var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https://dblp.org/pid/176/0380.bib&jsonp=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https://dblp.org/pid/176/0380.bib&jsonp=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https://dblp.org/pid/176/0380.bib&jsonp=1\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
  2. \n
  3. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
  4. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2024\n \n \n (9)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Text Diffusion with Reinforced Conditioning.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Wooldridge, M. J.; Dy, J. G.; and Natarajan, S., editor(s), Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pages 14069–14077, 2024. AAAI Press\n \n\n\n\n
\n\n\n\n \n \n \"TextPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/aaai/LiuYHZHWDSZ24,\n  author       = {Yuxuan Liu and\n                  Tianchi Yang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  editor       = {Michael J. Wooldridge and\n                  Jennifer G. Dy and\n                  Sriraam Natarajan},\n  title        = {Text Diffusion with Reinforced Conditioning},\n  booktitle    = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}\n                  2024, Thirty-Sixth Conference on Innovative Applications of Artificial\n                  Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances\n                  in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,\n                  Canada},\n  pages        = {14069--14077},\n  publisher    = {{AAAI} Press},\n  year         = {2024},\n  url          = {https://doi.org/10.1609/aaai.v38i12.29316},\n  doi          = {10.1609/AAAI.V38I12.29316},\n  timestamp    = {Tue, 02 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/aaai/LiuYHZHWDSZ24.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Domain Adaptation through Extended-Text Reading Comprehension.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Luo, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; Zhang, Q.; Wang, D.; and Zhuang, F.\n\n\n \n\n\n\n CoRR, abs/2401.07284. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2401-07284,\n  author       = {Ting Jiang and\n                  Shaohan Huang and\n                  Shengyue Luo and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang and\n                  Deqing Wang and\n                  Fuzhen Zhuang},\n  title        = {Improving Domain Adaptation through Extended-Text Reading Comprehension},\n  journal      = {CoRR},\n  volume       = {abs/2401.07284},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2401.07284},\n  doi          = {10.48550/ARXIV.2401.07284},\n  eprinttype    = {arXiv},\n  eprint       = {2401.07284},\n  timestamp    = {Thu, 01 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2401-07284.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models.\n \n \n \n \n\n\n \n Li, H.; Dong, Q.; Tang, Z.; Wang, C.; Zhang, X.; Huang, H.; Huang, S.; Huang, X.; Huang, Z.; Zhang, D.; Gu, Y.; Cheng, X.; Wang, X.; Chen, S.; Dong, L.; Lu, W.; Sui, Z.; Wang, B.; Lam, W.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2402.13064. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"SyntheticPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-13064,\n  author       = {Haoran Li and\n                  Qingxiu Dong and\n                  Zhengyang Tang and\n                  Chaojun Wang and\n                  Xingxing Zhang and\n                  Haoyang Huang and\n                  Shaohan Huang and\n                  Xiaolong Huang and\n                  Zeqiang Huang and\n                  Dongdong Zhang and\n                  Yuxian Gu and\n                  Xin Cheng and\n                  Xun Wang and\n                  Si{-}Qing Chen and\n                  Li Dong and\n                  Wei Lu and\n                  Zhifang Sui and\n                  Benyou Wang and\n                  Wai Lam and\n                  Furu Wei},\n  title        = {Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning\n                  for Language Models},\n  journal      = {CoRR},\n  volume       = {abs/2402.13064},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.13064},\n  doi          = {10.48550/ARXIV.2402.13064},\n  eprinttype    = {arXiv},\n  eprint       = {2402.13064},\n  timestamp    = {Thu, 21 Mar 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-13064.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Se\\(^\\mbox2\\): Sequential Example Selection for In-Context Learning.\n \n \n \n \n\n\n \n Liu, H.; Liu, J.; Huang, S.; Zhan, Y.; Sun, H.; Deng, W.; Wei, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2402.13874. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"Se\\(^\\mbox2\\):Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-13874,\n  author       = {Haoyu Liu and\n                  Jianfeng Liu and\n                  Shaohan Huang and\n                  Yuefeng Zhan and\n                  Hao Sun and\n                  Weiwei Deng and\n                  Furu Wei and\n                  Qi Zhang},\n  title        = {Se\\({}^{\\mbox{2}}\\): Sequential Example Selection for In-Context Learning},\n  journal      = {CoRR},\n  volume       = {abs/2402.13874},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.13874},\n  doi          = {10.48550/ARXIV.2402.13874},\n  eprinttype    = {arXiv},\n  eprint       = {2402.13874},\n  timestamp    = {Fri, 22 Mar 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-13874.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Text Diffusion with Reinforced Conditioning.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2402.14843. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"TextPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-14843,\n  author       = {Yuxuan Liu and\n                  Tianchi Yang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  title        = {Text Diffusion with Reinforced Conditioning},\n  journal      = {CoRR},\n  volume       = {abs/2402.14843},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.14843},\n  doi          = {10.48550/ARXIV.2402.14843},\n  eprinttype    = {arXiv},\n  eprint       = {2402.14843},\n  timestamp    = {Fri, 22 Mar 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-14843.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2402.15754. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"HD-Eval:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-15754,\n  author       = {Yuxuan Liu and\n                  Tianchi Yang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  title        = {HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical\n                  Criteria Decomposition},\n  journal      = {CoRR},\n  volume       = {abs/2402.15754},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.15754},\n  doi          = {10.48550/ARXIV.2402.15754},\n  eprinttype    = {arXiv},\n  eprint       = {2402.15754},\n  timestamp    = {Mon, 25 Mar 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-15754.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.\n \n \n \n \n\n\n \n Ma, S.; Wang, H.; Ma, L.; Wang, L.; Wang, W.; Huang, S.; Dong, L.; Wang, R.; Xue, J.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2402.17764. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-17764,\n  author       = {Shuming Ma and\n                  Hongyu Wang and\n                  Lingxiao Ma and\n                  Lei Wang and\n                  Wenhui Wang and\n                  Shaohan Huang and\n                  Li Dong and\n                  Ruiping Wang and\n                  Jilong Xue and\n                  Furu Wei},\n  title        = {The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits},\n  journal      = {CoRR},\n  volume       = {abs/2402.17764},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.17764},\n  doi          = {10.48550/ARXIV.2402.17764},\n  eprinttype    = {arXiv},\n  eprint       = {2402.17764},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-17764.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n ResLoRA: Identity Residual Mapping in Low-Rank Adaption.\n \n \n \n \n\n\n \n Shi, S.; Huang, S.; Song, M.; Li, Z.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2402.18039. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ResLoRA:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-18039,\n  author       = {Shuhua Shi and\n                  Shaohan Huang and\n                  Minghui Song and\n                  Zhoujun Li and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  title        = {ResLoRA: Identity Residual Mapping in Low-Rank Adaption},\n  journal      = {CoRR},\n  volume       = {abs/2402.18039},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2402.18039},\n  doi          = {10.48550/ARXIV.2402.18039},\n  eprinttype    = {arXiv},\n  eprint       = {2402.18039},\n  timestamp    = {Tue, 26 Mar 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-18039.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Exploring the Comprehension of ChatGPT in Traditional Chinese Medicine Knowledge.\n \n \n \n \n\n\n \n Li, Y.; Huang, S.; Qi, J.; Quan, L.; Han, D.; and Luan, Z.\n\n\n \n\n\n\n CoRR, abs/2403.09164. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ExploringPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2403-09164,\n  author       = {Yizhen Li and\n                  Shaohan Huang and\n                  Jiaxing Qi and\n                  Lei Quan and\n                  Dongran Han and\n                  Zhongzhi Luan},\n  title        = {Exploring the Comprehension of ChatGPT in Traditional Chinese Medicine\n                  Knowledge},\n  journal      = {CoRR},\n  volume       = {abs/2403.09164},\n  year         = {2024},\n  url          = {https://doi.org/10.48550/arXiv.2403.09164},\n  doi          = {10.48550/ARXIV.2403.09164},\n  eprinttype    = {arXiv},\n  eprint       = {2403.09164},\n  timestamp    = {Fri, 05 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2403-09164.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2023\n \n \n (30)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Improving Log-Based Anomaly Detection by Pre-Training Hierarchical Transformers.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; Wang, H.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n IEEE Trans. Computers, 72(9): 2656–2667. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/tc/HuangLFWYL23,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  He Wang and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  title        = {Improving Log-Based Anomaly Detection by Pre-Training Hierarchical\n                  Transformers},\n  journal      = {{IEEE} Trans. Computers},\n  volume       = {72},\n  number       = {9},\n  pages        = {2656--2667},\n  year         = {2023},\n  url          = {https://doi.org/10.1109/TC.2023.3257518},\n  doi          = {10.1109/TC.2023.3257518},\n  timestamp    = {Fri, 18 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/tc/HuangLFWYL23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LogEncoder: Log-Based Contrastive Representation Learning for Anomaly Detection.\n \n \n \n \n\n\n \n Qi, J.; Luan, Z.; Huang, S.; Fung, C. J.; Yang, H.; Li, H.; Zhu, D.; and Qian, D.\n\n\n \n\n\n\n IEEE Trans. Netw. Serv. Manag., 20(2): 1378–1391. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LogEncoder:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/tnsm/QiLHFYLZQ23,\n  author       = {Jiaxing Qi and\n                  Zhongzhi Luan and\n                  Shaohan Huang and\n                  Carol J. Fung and\n                  Hailong Yang and\n                  Hanlu Li and\n                  Danfeng Zhu and\n                  Depei Qian},\n  title        = {LogEncoder: Log-Based Contrastive Representation Learning for Anomaly\n                  Detection},\n  journal      = {{IEEE} Trans. Netw. Serv. Manag.},\n  volume       = {20},\n  number       = {2},\n  pages        = {1378--1391},\n  year         = {2023},\n  url          = {https://doi.org/10.1109/TNSM.2023.3239522},\n  doi          = {10.1109/TNSM.2023.3239522},\n  timestamp    = {Fri, 07 Jul 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/tnsm/QiLHFYLZQ23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MoEC: Mixture of Expert Clusters.\n \n \n \n \n\n\n \n Xie, Y.; Huang, S.; Chen, T.; and Wei, F.\n\n\n \n\n\n\n In Williams, B.; Chen, Y.; and Neville, J., editor(s), Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023, pages 13807–13815, 2023. AAAI Press\n \n\n\n\n
\n\n\n\n \n \n \"MoEC:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/aaai/XieHCW23,\n  author       = {Yuan Xie and\n                  Shaohan Huang and\n                  Tianyu Chen and\n                  Furu Wei},\n  editor       = {Brian Williams and\n                  Yiling Chen and\n                  Jennifer Neville},\n  title        = {MoEC: Mixture of Expert Clusters},\n  booktitle    = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}\n                  2023, Thirty-Fifth Conference on Innovative Applications of Artificial\n                  Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances\n                  in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February\n                  7-14, 2023},\n  pages        = {13807--13815},\n  publisher    = {{AAAI} Press},\n  year         = {2023},\n  url          = {https://doi.org/10.1609/aaai.v37i11.26617},\n  doi          = {10.1609/AAAI.V37I11.26617},\n  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/aaai/XieHCW23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Pre-training Language Model as a Multi-perspective Course Learner.\n \n \n \n \n\n\n \n Chen, B.; Huang, S.; Zhang, Z.; Guo, W.; Ling, Z.; Huang, H.; Wei, F.; Deng, W.; and Zhang, Q.\n\n\n \n\n\n\n In Rogers, A.; Boyd-Graber, J. L.; and Okazaki, N., editor(s), Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 114–128, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Pre-trainingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/ChenHZGLHWDZ23,\n  author       = {Beiduo Chen and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Wu Guo and\n                  Zhenhua Ling and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Qi Zhang},\n  editor       = {Anna Rogers and\n                  Jordan L. Boyd{-}Graber and\n                  Naoaki Okazaki},\n  title        = {Pre-training Language Model as a Multi-perspective Course Learner},\n  booktitle    = {Findings of the Association for Computational Linguistics: {ACL} 2023,\n                  Toronto, Canada, July 9-14, 2023},\n  pages        = {114--128},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.findings-acl.9},\n  doi          = {10.18653/V1/2023.FINDINGS-ACL.9},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/acl/ChenHZGLHWDZ23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Dual-Alignment Pre-training for Cross-lingual Sentence Embedding.\n \n \n \n \n\n\n \n Li, Z.; Huang, S.; Zhang, Z.; Deng, Z.; Lou, Q.; Huang, H.; Jiao, J.; Wei, F.; Deng, W.; and Zhang, Q.\n\n\n \n\n\n\n In Rogers, A.; Boyd-Graber, J. L.; and Okazaki, N., editor(s), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 3466–3478, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Dual-AlignmentPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/LiHZDLHJWDZ23,\n  author       = {Ziheng Li and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Zhi{-}Hong Deng and\n                  Qiang Lou and\n                  Haizhen Huang and\n                  Jian Jiao and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Qi Zhang},\n  editor       = {Anna Rogers and\n                  Jordan L. Boyd{-}Graber and\n                  Naoaki Okazaki},\n  title        = {Dual-Alignment Pre-training for Cross-lingual Sentence Embedding},\n  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational\n                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,\n                  July 9-14, 2023},\n  pages        = {3466--3478},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.acl-long.191},\n  doi          = {10.18653/V1/2023.ACL-LONG.191},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/acl/LiHZDLHJWDZ23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator.\n \n \n \n \n\n\n \n Yang, J.; Ma, S.; Dong, L.; Huang, S.; Huang, H.; Yin, Y.; Zhang, D.; Yang, L.; Wei, F.; and Li, Z.\n\n\n \n\n\n\n In Rogers, A.; Boyd-Graber, J. L.; and Okazaki, N., editor(s), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 9394–9412, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"GanLM:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/YangM0HHYZYWL23,\n  author       = {Jian Yang and\n                  Shuming Ma and\n                  Li Dong and\n                  Shaohan Huang and\n                  Haoyang Huang and\n                  Yuwei Yin and\n                  Dongdong Zhang and\n                  Liqun Yang and\n                  Furu Wei and\n                  Zhoujun Li},\n  editor       = {Anna Rogers and\n                  Jordan L. Boyd{-}Graber and\n                  Naoaki Okazaki},\n  title        = {GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator},\n  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational\n                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,\n                  July 9-14, 2023},\n  pages        = {9394--9412},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.acl-long.522},\n  doi          = {10.18653/V1/2023.ACL-LONG.522},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/acl/YangM0HHYZYWL23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Length-Extrapolatable Transformer.\n \n \n \n \n\n\n \n Sun, Y.; Dong, L.; Patra, B.; Ma, S.; Huang, S.; Benhaim, A.; Chaudhary, V.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Rogers, A.; Boyd-Graber, J. L.; and Okazaki, N., editor(s), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 14590–14604, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/SunDPMHBCSW23,\n  author       = {Yutao Sun and\n                  Li Dong and\n                  Barun Patra and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Alon Benhaim and\n                  Vishrav Chaudhary and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Anna Rogers and\n                  Jordan L. Boyd{-}Graber and\n                  Naoaki Okazaki},\n  title        = {A Length-Extrapolatable Transformer},\n  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational\n                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,\n                  July 9-14, 2023},\n  pages        = {14590--14604},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.acl-long.816},\n  doi          = {10.18653/V1/2023.ACL-LONG.816},\n  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/SunDPMHBCSW23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning.\n \n \n \n \n\n\n \n Patra, B.; Singhal, S.; Huang, S.; Chi, Z.; Dong, L.; Wei, F.; Chaudhary, V.; and Song, X.\n\n\n \n\n\n\n In Rogers, A.; Boyd-Graber, J. L.; and Okazaki, N., editor(s), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 15354–15373, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"BeyondPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/PatraSHC0WCS23,\n  author       = {Barun Patra and\n                  Saksham Singhal and\n                  Shaohan Huang and\n                  Zewen Chi and\n                  Li Dong and\n                  Furu Wei and\n                  Vishrav Chaudhary and\n                  Xia Song},\n  editor       = {Anna Rogers and\n                  Jordan L. Boyd{-}Graber and\n                  Naoaki Okazaki},\n  title        = {Beyond English-Centric Bitexts for Better Multilingual Language Representation\n                  Learning},\n  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational\n                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,\n                  July 9-14, 2023},\n  pages        = {15354--15373},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.acl-long.856},\n  doi          = {10.18653/V1/2023.ACL-LONG.856},\n  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/PatraSHC0WCS23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Democratizing Reasoning Ability: Tailored Learning from Large Language Model.\n \n \n \n \n\n\n \n Wang, Z.; Huang, S.; Liu, Y.; Wang, J.; Song, M.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Bouamor, H.; Pino, J.; and Bali, K., editor(s), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 1948–1966, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"DemocratizingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/WangHLWSZHWDSZ23,\n  author       = {Zhaoyang Wang and\n                  Shaohan Huang and\n                  Yuxuan Liu and\n                  Jiahai Wang and\n                  Minghui Song and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  editor       = {Houda Bouamor and\n                  Juan Pino and\n                  Kalika Bali},\n  title        = {Democratizing Reasoning Ability: Tailored Learning from Large Language\n                  Model},\n  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},\n  pages        = {1948--1966},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.emnlp-main.120},\n  doi          = {10.18653/V1/2023.EMNLP-MAIN.120},\n  timestamp    = {Fri, 12 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/emnlp/WangHLWSZHWDSZ23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; Bi, J.; Zhan, Y.; Liu, J.; Wang, Y.; Sun, H.; Wei, F.; Deng, W.; and Zhang, Q.\n\n\n \n\n\n\n In Bouamor, H.; Pino, J.; and Bali, K., editor(s), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 12318–12337, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"UPRISE:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/ChengHBZLW0WDZ23,\n  author       = {Daixuan Cheng and\n                  Shaohan Huang and\n                  Junyu Bi and\n                  Yuefeng Zhan and\n                  Jianfeng Liu and\n                  Yujing Wang and\n                  Hao Sun and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Qi Zhang},\n  editor       = {Houda Bouamor and\n                  Juan Pino and\n                  Kalika Bali},\n  title        = {{UPRISE:} Universal Prompt Retrieval for Improving Zero-Shot Evaluation},\n  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},\n  pages        = {12318--12337},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2023},\n  url          = {https://doi.org/10.18653/v1/2023.emnlp-main.758},\n  doi          = {10.18653/V1/2023.EMNLP-MAIN.758},\n  timestamp    = {Fri, 12 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/emnlp/ChengHBZLW0WDZ23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LogGPT: Exploring ChatGPT for Log-Based Anomaly Detection.\n \n \n \n \n\n\n \n Qi, J.; Huang, S.; Luan, Z.; Yang, S.; Fung, C. J.; Yang, H.; Qian, D.; Shang, J.; Xiao, Z.; and Wu, Z.\n\n\n \n\n\n\n In IEEE International Conference on High Performance Computing & Communications, Data Science & Systems, Smart City & Dependability in Sensor, Cloud & Big Data Systems & Application, HPCC/DSS/SmartCity/DependSys 2023, Melbourne, Australia, December 17-21, 2023, pages 273–280, 2023. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"LogGPT:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/hpcc/QiHLYFYQSXW23,\n  author       = {Jiaxing Qi and\n                  Shaohan Huang and\n                  Zhongzhi Luan and\n                  Shu Yang and\n                  Carol J. Fung and\n                  Hailong Yang and\n                  Depei Qian and\n                  Jing Shang and\n                  Zhiwen Xiao and\n                  Zhihui Wu},\n  title        = {LogGPT: Exploring ChatGPT for Log-Based Anomaly Detection},\n  booktitle    = {{IEEE} International Conference on High Performance Computing {\\&}\n                  Communications, Data Science {\\&} Systems, Smart City {\\&} Dependability\n                  in Sensor, Cloud {\\&} Big Data Systems {\\&} Application, HPCC/DSS/SmartCity/DependSys\n                  2023, Melbourne, Australia, December 17-21, 2023},\n  pages        = {273--280},\n  publisher    = {{IEEE}},\n  year         = {2023},\n  url          = {https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys60770.2023.00045},\n  doi          = {10.1109/HPCC-DSS-SMARTCITY-DEPENDSYS60770.2023.00045},\n  timestamp    = {Wed, 10 Apr 2024 17:07:58 +0200},\n  biburl       = {https://dblp.org/rec/conf/hpcc/QiHLYFYQSXW23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Magneto: A Foundation Transformer.\n \n \n \n \n\n\n \n Wang, H.; Ma, S.; Huang, S.; Dong, L.; Wang, W.; Peng, Z.; Wu, Y.; Bajaj, P.; Singhal, S.; Benhaim, A.; Patra, B.; Liu, Z.; Chaudhary, V.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Krause, A.; Brunskill, E.; Cho, K.; Engelhardt, B.; Sabato, S.; and Scarlett, J., editor(s), International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202, of Proceedings of Machine Learning Research, pages 36077–36092, 2023. PMLR\n \n\n\n\n
\n\n\n\n \n \n \"Magneto:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/icml/WangMH0WPWBSBPL23,\n  author       = {Hongyu Wang and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Li Dong and\n                  Wenhui Wang and\n                  Zhiliang Peng and\n                  Yu Wu and\n                  Payal Bajaj and\n                  Saksham Singhal and\n                  Alon Benhaim and\n                  Barun Patra and\n                  Zhun Liu and\n                  Vishrav Chaudhary and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Andreas Krause and\n                  Emma Brunskill and\n                  Kyunghyun Cho and\n                  Barbara Engelhardt and\n                  Sivan Sabato and\n                  Jonathan Scarlett},\n  title        = {Magneto: {A} Foundation Transformer},\n  booktitle    = {International Conference on Machine Learning, {ICML} 2023, 23-29 July\n                  2023, Honolulu, Hawaii, {USA}},\n  series       = {Proceedings of Machine Learning Research},\n  volume       = {202},\n  pages        = {36077--36092},\n  publisher    = {{PMLR}},\n  year         = {2023},\n  url          = {https://proceedings.mlr.press/v202/wang23u.html},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/icml/WangMH0WPWBSBPL23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Language Is Not All You Need: Aligning Perception with Language Models.\n \n \n \n \n\n\n \n Huang, S.; Dong, L.; Wang, W.; Hao, Y.; Singhal, S.; Ma, S.; Lv, T.; Cui, L.; Mohammed, O. K.; Patra, B.; Liu, Q.; Aggarwal, K.; Chi, Z.; Bjorck, N. J. B.; Chaudhary, V.; Som, S.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Oh, A.; Naumann, T.; Globerson, A.; Saenko, K.; Hardt, M.; and Levine, S., editor(s), Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023. \n \n\n\n\n
\n\n\n\n \n \n \"LanguagePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/Huang0WHSML0MPL23,\n  author       = {Shaohan Huang and\n                  Li Dong and\n                  Wenhui Wang and\n                  Yaru Hao and\n                  Saksham Singhal and\n                  Shuming Ma and\n                  Tengchao Lv and\n                  Lei Cui and\n                  Owais Khan Mohammed and\n                  Barun Patra and\n                  Qiang Liu and\n                  Kriti Aggarwal and\n                  Zewen Chi and\n                  Nils Johan Bertil Bjorck and\n                  Vishrav Chaudhary and\n                  Subhojit Som and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Alice Oh and\n                  Tristan Naumann and\n                  Amir Globerson and\n                  Kate Saenko and\n                  Moritz Hardt and\n                  Sergey Levine},\n  title        = {Language Is Not All You Need: Aligning Perception with Language Models},\n  booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference\n                  on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,\n                  LA, USA, December 10 - 16, 2023},\n  year         = {2023},\n  url          = {http://papers.nips.cc/paper\\_files/paper/2023/hash/e425b75bac5742a008d643826428787c-Abstract-Conference.html},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/nips/Huang0WHSML0MPL23.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Language Is Not All You Need: Aligning Perception with Language Models.\n \n \n \n \n\n\n \n Huang, S.; Dong, L.; Wang, W.; Hao, Y.; Singhal, S.; Ma, S.; Lv, T.; Cui, L.; Mohammed, O. K.; Patra, B.; Liu, Q.; Aggarwal, K.; Chi, Z.; Bjorck, J.; Chaudhary, V.; Som, S.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2302.14045. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LanguagePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2302-14045,\n  author       = {Shaohan Huang and\n                  Li Dong and\n                  Wenhui Wang and\n                  Yaru Hao and\n                  Saksham Singhal and\n                  Shuming Ma and\n                  Tengchao Lv and\n                  Lei Cui and\n                  Owais Khan Mohammed and\n                  Barun Patra and\n                  Qiang Liu and\n                  Kriti Aggarwal and\n                  Zewen Chi and\n                  Johan Bjorck and\n                  Vishrav Chaudhary and\n                  Subhojit Som and\n                  Xia Song and\n                  Furu Wei},\n  title        = {Language Is Not All You Need: Aligning Perception with Language Models},\n  journal      = {CoRR},\n  volume       = {abs/2302.14045},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2302.14045},\n  doi          = {10.48550/ARXIV.2302.14045},\n  eprinttype    = {arXiv},\n  eprint       = {2302.14045},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-14045.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; Bi, J.; Zhan, Y.; Liu, J.; Wang, Y.; Sun, H.; Wei, F.; Deng, D.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2303.08518. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"UPRISE:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2303-08518,\n  author       = {Daixuan Cheng and\n                  Shaohan Huang and\n                  Junyu Bi and\n                  Yuefeng Zhan and\n                  Jianfeng Liu and\n                  Yujing Wang and\n                  Hao Sun and\n                  Furu Wei and\n                  Denvy Deng and\n                  Qi Zhang},\n  title        = {{UPRISE:} Universal Prompt Retrieval for Improving Zero-Shot Evaluation},\n  journal      = {CoRR},\n  volume       = {abs/2303.08518},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2303.08518},\n  doi          = {10.48550/ARXIV.2303.08518},\n  eprinttype    = {arXiv},\n  eprint       = {2303.08518},\n  timestamp    = {Fri, 05 May 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2303-08518.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LogQA: Question Answering in Unstructured Logs.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; Qi, J.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n CoRR, abs/2303.11715. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LogQA:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2303-11715,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Jiaxing Qi and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  title        = {LogQA: Question Answering in Unstructured Logs},\n  journal      = {CoRR},\n  volume       = {abs/2303.11715},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2303.11715},\n  doi          = {10.48550/ARXIV.2303.11715},\n  eprinttype    = {arXiv},\n  eprint       = {2303.11715},\n  timestamp    = {Sun, 16 Apr 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2303-11715.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Pre-training Language Model as a Multi-perspective Course Learner.\n \n \n \n \n\n\n \n Chen, B.; Huang, S.; Zhang, Z.; Guo, W.; Ling, Z.; Huang, H.; Wei, F.; Deng, W.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2305.03981. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"Pre-trainingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2305-03981,\n  author       = {Beiduo Chen and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Wu Guo and\n                  Zhenhua Ling and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Qi Zhang},\n  title        = {Pre-training Language Model as a Multi-perspective Course Learner},\n  journal      = {CoRR},\n  volume       = {abs/2305.03981},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2305.03981},\n  doi          = {10.48550/ARXIV.2305.03981},\n  eprinttype    = {arXiv},\n  eprint       = {2305.03981},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-03981.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Dual-Alignment Pre-training for Cross-lingual Sentence Embedding.\n \n \n \n \n\n\n \n Li, Z.; Huang, S.; Zhang, Z.; Deng, Z.; Lou, Q.; Huang, H.; Jiao, J.; Wei, F.; Deng, W.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2305.09148. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"Dual-AlignmentPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2305-09148,\n  author       = {Ziheng Li and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Zhi{-}Hong Deng and\n                  Qiang Lou and\n                  Haizhen Huang and\n                  Jian Jiao and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Qi Zhang},\n  title        = {Dual-Alignment Pre-training for Cross-lingual Sentence Embedding},\n  journal      = {CoRR},\n  volume       = {abs/2305.09148},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2305.09148},\n  doi          = {10.48550/ARXIV.2305.09148},\n  eprinttype    = {arXiv},\n  eprint       = {2305.09148},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-09148.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning Music Sequence Representation from Text Supervision.\n \n \n \n \n\n\n \n Chen, T.; Xie, Y.; Zhang, S.; Huang, S.; Zhou, H.; and Li, J.\n\n\n \n\n\n\n CoRR, abs/2305.19602. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2305-19602,\n  author       = {Tianyu Chen and\n                  Yuan Xie and\n                  Shuai Zhang and\n                  Shaohan Huang and\n                  Haoyi Zhou and\n                  Jianxin Li},\n  title        = {Learning Music Sequence Representation from Text Supervision},\n  journal      = {CoRR},\n  volume       = {abs/2305.19602},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2305.19602},\n  doi          = {10.48550/ARXIV.2305.19602},\n  eprinttype    = {arXiv},\n  eprint       = {2305.19602},\n  timestamp    = {Mon, 14 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-19602.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Kosmos-2: Grounding Multimodal Large Language Models to the World.\n \n \n \n \n\n\n \n Peng, Z.; Wang, W.; Dong, L.; Hao, Y.; Huang, S.; Ma, S.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2306.14824. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"Kosmos-2:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2306-14824,\n  author       = {Zhiliang Peng and\n                  Wenhui Wang and\n                  Li Dong and\n                  Yaru Hao and\n                  Shaohan Huang and\n                  Shuming Ma and\n                  Furu Wei},\n  title        = {Kosmos-2: Grounding Multimodal Large Language Models to the World},\n  journal      = {CoRR},\n  volume       = {abs/2306.14824},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2306.14824},\n  doi          = {10.48550/ARXIV.2306.14824},\n  eprinttype    = {arXiv},\n  eprint       = {2306.14824},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-14824.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LongNet: Scaling Transformers to 1, 000, 000, 000 Tokens.\n \n \n \n \n\n\n \n Ding, J.; Ma, S.; Dong, L.; Zhang, X.; Huang, S.; Wang, W.; Zheng, N.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2307.02486. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LongNet:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2307-02486,\n  author       = {Jiayu Ding and\n                  Shuming Ma and\n                  Li Dong and\n                  Xingxing Zhang and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Nanning Zheng and\n                  Furu Wei},\n  title        = {LongNet: Scaling Transformers to 1, 000, 000, 000 Tokens},\n  journal      = {CoRR},\n  volume       = {abs/2307.02486},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2307.02486},\n  doi          = {10.48550/ARXIV.2307.02486},\n  eprinttype    = {arXiv},\n  eprint       = {2307.02486},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-02486.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Retentive Network: A Successor to Transformer for Large Language Models.\n \n \n \n \n\n\n \n Sun, Y.; Dong, L.; Huang, S.; Ma, S.; Xia, Y.; Xue, J.; Wang, J.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2307.08621. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"RetentivePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2307-08621,\n  author       = {Yutao Sun and\n                  Li Dong and\n                  Shaohan Huang and\n                  Shuming Ma and\n                  Yuqing Xia and\n                  Jilong Xue and\n                  Jianyong Wang and\n                  Furu Wei},\n  title        = {Retentive Network: {A} Successor to Transformer for Large Language\n                  Models},\n  journal      = {CoRR},\n  volume       = {abs/2307.08621},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2307.08621},\n  doi          = {10.48550/ARXIV.2307.08621},\n  eprinttype    = {arXiv},\n  eprint       = {2307.08621},\n  timestamp    = {Tue, 25 Jul 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-08621.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Scaling Sentence Embeddings with Large Language Models.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Luan, Z.; Wang, D.; and Zhuang, F.\n\n\n \n\n\n\n CoRR, abs/2307.16645. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"ScalingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2307-16645,\n  author       = {Ting Jiang and\n                  Shaohan Huang and\n                  Zhongzhi Luan and\n                  Deqing Wang and\n                  Fuzhen Zhuang},\n  title        = {Scaling Sentence Embeddings with Large Language Models},\n  journal      = {CoRR},\n  volume       = {abs/2307.16645},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2307.16645},\n  doi          = {10.48550/ARXIV.2307.16645},\n  eprinttype    = {arXiv},\n  eprint       = {2307.16645},\n  timestamp    = {Wed, 02 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-16645.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LogGPT: Exploring ChatGPT for Log-Based Anomaly Detection.\n \n \n \n \n\n\n \n Qi, J.; Huang, S.; Luan, Z.; Fung, C. J.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n CoRR, abs/2309.01189. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"LogGPT:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2309-01189,\n  author       = {Jiaxing Qi and\n                  Shaohan Huang and\n                  Zhongzhi Luan and\n                  Carol J. Fung and\n                  Hailong Yang and\n                  Depei Qian},\n  title        = {LogGPT: Exploring ChatGPT for Log-Based Anomaly Detection},\n  journal      = {CoRR},\n  volume       = {abs/2309.01189},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2309.01189},\n  doi          = {10.48550/ARXIV.2309.01189},\n  eprinttype    = {arXiv},\n  eprint       = {2309.01189},\n  timestamp    = {Mon, 11 Sep 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-01189.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Adapting Large Language Models via Reading Comprehension.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2309.09530. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"AdaptingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2309-09530,\n  author       = {Daixuan Cheng and\n                  Shaohan Huang and\n                  Furu Wei},\n  title        = {Adapting Large Language Models via Reading Comprehension},\n  journal      = {CoRR},\n  volume       = {abs/2309.09530},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2309.09530},\n  doi          = {10.48550/ARXIV.2309.09530},\n  eprinttype    = {arXiv},\n  eprint       = {2309.09530},\n  timestamp    = {Fri, 22 Sep 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-09530.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Kosmos-2.5: A Multimodal Literate Model.\n \n \n \n \n\n\n \n Lv, T.; Huang, Y.; Chen, J.; Cui, L.; Ma, S.; Chang, Y.; Huang, S.; Wang, W.; Dong, L.; Luo, W.; Wu, S.; Wang, G.; Zhang, C.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2309.11419. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"Kosmos-2.5:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2309-11419,\n  author       = {Tengchao Lv and\n                  Yupan Huang and\n                  Jingye Chen and\n                  Lei Cui and\n                  Shuming Ma and\n                  Yaoyao Chang and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Li Dong and\n                  Weiyao Luo and\n                  Shaoxiang Wu and\n                  Guoxin Wang and\n                  Cha Zhang and\n                  Furu Wei},\n  title        = {Kosmos-2.5: {A} Multimodal Literate Model},\n  journal      = {CoRR},\n  volume       = {abs/2309.11419},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2309.11419},\n  doi          = {10.48550/ARXIV.2309.11419},\n  eprinttype    = {arXiv},\n  eprint       = {2309.11419},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-11419.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Calibrating LLM-Based Evaluator.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2309.13308. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"CalibratingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2309-13308,\n  author       = {Yuxuan Liu and\n                  Tianchi Yang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  title        = {Calibrating LLM-Based Evaluator},\n  journal      = {CoRR},\n  volume       = {abs/2309.13308},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2309.13308},\n  doi          = {10.48550/ARXIV.2309.13308},\n  eprinttype    = {arXiv},\n  eprint       = {2309.13308},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-13308.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Kosmos-G: Generating Images in Context with Multimodal Large Language Models.\n \n \n \n \n\n\n \n Pan, X.; Dong, L.; Huang, S.; Peng, Z.; Chen, W.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2310.02992. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"Kosmos-G:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2310-02992,\n  author       = {Xichen Pan and\n                  Li Dong and\n                  Shaohan Huang and\n                  Zhiliang Peng and\n                  Wenhu Chen and\n                  Furu Wei},\n  title        = {Kosmos-G: Generating Images in Context with Multimodal Large Language\n                  Models},\n  journal      = {CoRR},\n  volume       = {abs/2310.02992},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2310.02992},\n  doi          = {10.48550/ARXIV.2310.02992},\n  eprinttype    = {arXiv},\n  eprint       = {2310.02992},\n  timestamp    = {Thu, 19 Oct 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-02992.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n BitNet: Scaling 1-bit Transformers for Large Language Models.\n \n \n \n \n\n\n \n Wang, H.; Ma, S.; Dong, L.; Huang, S.; Wang, H.; Ma, L.; Yang, F.; Wang, R.; Wu, Y.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2310.11453. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"BitNet:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2310-11453,\n  author       = {Hongyu Wang and\n                  Shuming Ma and\n                  Li Dong and\n                  Shaohan Huang and\n                  Huaijie Wang and\n                  Lingxiao Ma and\n                  Fan Yang and\n                  Ruiping Wang and\n                  Yi Wu and\n                  Furu Wei},\n  title        = {BitNet: Scaling 1-bit Transformers for Large Language Models},\n  journal      = {CoRR},\n  volume       = {abs/2310.11453},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2310.11453},\n  doi          = {10.48550/ARXIV.2310.11453},\n  eprinttype    = {arXiv},\n  eprint       = {2310.11453},\n  timestamp    = {Tue, 02 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-11453.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Democratizing Reasoning Ability: Tailored Learning from Large Language Model.\n \n \n \n \n\n\n \n Wang, Z.; Huang, S.; Liu, Y.; Wang, J.; Song, M.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2310.13332. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"DemocratizingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2310-13332,\n  author       = {Zhaoyang Wang and\n                  Shaohan Huang and\n                  Yuxuan Liu and\n                  Jiahai Wang and\n                  Minghui Song and\n                  Zihan Zhang and\n                  Haizhen Huang and\n                  Furu Wei and\n                  Weiwei Deng and\n                  Feng Sun and\n                  Qi Zhang},\n  title        = {Democratizing Reasoning Ability: Tailored Learning from Large Language\n                  Model},\n  journal      = {CoRR},\n  volume       = {abs/2310.13332},\n  year         = {2023},\n  url          = {https://doi.org/10.48550/arXiv.2310.13332},\n  doi          = {10.48550/ARXIV.2310.13332},\n  eprinttype    = {arXiv},\n  eprint       = {2310.13332},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-13332.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (26)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Impacts of COVID-19 on the Return and Volatility Nexus among Cryptocurrency Market.\n \n \n \n \n\n\n \n Sui, X.; Shi, G.; Hou, G.; Huang, S.; and Li, Y.\n\n\n \n\n\n\n Complex., 2022: 5346080:1–5346080:15. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"ImpactsPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/complexity/SuiSHHL22,\n  author       = {Xin Sui and\n                  Guifen Shi and\n                  Guanchong Hou and\n                  Shaohan Huang and\n                  Yanshuang Li},\n  title        = {Impacts of {COVID-19} on the Return and Volatility Nexus among Cryptocurrency\n                  Market},\n  journal      = {Complex.},\n  volume       = {2022},\n  pages        = {5346080:1--5346080:15},\n  year         = {2022},\n  url          = {https://doi.org/10.1155/2022/5346080},\n  doi          = {10.1155/2022/5346080},\n  timestamp    = {Mon, 26 Sep 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/complexity/SuiSHHL22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n REVAL: Recommend Which Variables to Log With Pretrained Model and Graph Neural Network.\n \n \n \n \n\n\n \n Dai, S.; Luan, Z.; Huang, S.; Fung, C. J.; Wang, H.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n IEEE Trans. Netw. Serv. Manag., 19(4): 4045–4057. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"REVAL:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/tnsm/DaiLHFWYQ22,\n  author       = {Shaozhi Dai and\n                  Zhongzhi Luan and\n                  Shaohan Huang and\n                  Carol J. Fung and\n                  He Wang and\n                  Hailong Yang and\n                  Depei Qian},\n  title        = {{REVAL:} Recommend Which Variables to Log With Pretrained Model and\n                  Graph Neural Network},\n  journal      = {{IEEE} Trans. Netw. Serv. Manag.},\n  volume       = {19},\n  number       = {4},\n  pages        = {4045--4057},\n  year         = {2022},\n  url          = {https://doi.org/10.1109/TNSM.2022.3209317},\n  doi          = {10.1109/TNSM.2022.3209317},\n  timestamp    = {Fri, 10 Feb 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/tnsm/DaiLHFWYQ22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption.\n \n \n \n \n\n\n \n Chen, T.; Bao, H.; Huang, S.; Dong, L.; Jiao, B.; Jiang, D.; Zhou, H.; Li, J.; and Wei, F.\n\n\n \n\n\n\n In Muresan, S.; Nakov, P.; and Villavicencio, A., editor(s), Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 3510–3520, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"THE-X:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/ChenBHDJJZLW22,\n  author       = {Tianyu Chen and\n                  Hangbo Bao and\n                  Shaohan Huang and\n                  Li Dong and\n                  Binxing Jiao and\n                  Daxin Jiang and\n                  Haoyi Zhou and\n                  Jianxin Li and\n                  Furu Wei},\n  editor       = {Smaranda Muresan and\n                  Preslav Nakov and\n                  Aline Villavicencio},\n  title        = {{THE-X:} Privacy-Preserving Transformer Inference with Homomorphic\n                  Encryption},\n  booktitle    = {Findings of the Association for Computational Linguistics: {ACL} 2022,\n                  Dublin, Ireland, May 22-27, 2022},\n  pages        = {3510--3520},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2022},\n  url          = {https://doi.org/10.18653/v1/2022.findings-acl.277},\n  doi          = {10.18653/V1/2022.FINDINGS-ACL.277},\n  timestamp    = {Thu, 06 Apr 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/ChenBHDJJZLW22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n XLM-E: Cross-lingual Language Model Pre-training via ELECTRA.\n \n \n \n \n\n\n \n Chi, Z.; Huang, S.; Dong, L.; Ma, S.; Zheng, B.; Singhal, S.; Bajaj, P.; Song, X.; Mao, X.; Huang, H.; and Wei, F.\n\n\n \n\n\n\n In Muresan, S.; Nakov, P.; and Villavicencio, A., editor(s), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 6170–6182, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"XLM-E:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/ChiH0MZSBSMHW22,\n  author       = {Zewen Chi and\n                  Shaohan Huang and\n                  Li Dong and\n                  Shuming Ma and\n                  Bo Zheng and\n                  Saksham Singhal and\n                  Payal Bajaj and\n                  Xia Song and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Furu Wei},\n  editor       = {Smaranda Muresan and\n                  Preslav Nakov and\n                  Aline Villavicencio},\n  title        = {{XLM-E:} Cross-lingual Language Model Pre-training via {ELECTRA}},\n  booktitle    = {Proceedings of the 60th Annual Meeting of the Association for Computational\n                  Linguistics (Volume 1: Long Papers), {ACL} 2022, Dublin, Ireland,\n                  May 22-27, 2022},\n  pages        = {6170--6182},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2022},\n  url          = {https://doi.org/10.18653/v1/2022.acl-long.427},\n  doi          = {10.18653/V1/2022.ACL-LONG.427},\n  timestamp    = {Mon, 01 Aug 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/ChiH0MZSBSMHW22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Black-box Attacks to Log-based Anomaly Detection.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n In Charalambides, M.; Papadimitriou, P.; Cerroni, W.; Kanhere, S. S.; and Mamatas, L., editor(s), 18th International Conference on Network and Service Management, CNSM 2022, Thessaloniki, Greece, October 31 - Nov. 4, 2022, pages 310–316, 2022. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"Black-boxPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/cnsm/HuangLFYL22,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  editor       = {Marinos Charalambides and\n                  Panagiotis Papadimitriou and\n                  Walter Cerroni and\n                  Salil S. Kanhere and\n                  Lefteris Mamatas},\n  title        = {Black-box Attacks to Log-based Anomaly Detection},\n  booktitle    = {18th International Conference on Network and Service Management, {CNSM}\n                  2022, Thessaloniki, Greece, October 31 - Nov. 4, 2022},\n  pages        = {310--316},\n  publisher    = {{IEEE}},\n  year         = {2022},\n  url          = {https://doi.org/10.23919/CNSM55787.2022.9964935},\n  doi          = {10.23919/CNSM55787.2022.9964935},\n  timestamp    = {Thu, 08 Dec 2022 15:05:27 +0100},\n  biburl       = {https://dblp.org/rec/conf/cnsm/HuangLFYL22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation.\n \n \n \n \n\n\n \n Yang, J.; Huang, S.; Ma, S.; Yin, Y.; Dong, L.; Zhang, D.; Guo, H.; Li, Z.; and Wei, F.\n\n\n \n\n\n\n In Goldberg, Y.; Kozareva, Z.; and Zhang, Y., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 486–496, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"CROP:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/YangHMY0ZGLW22,\n  author       = {Jian Yang and\n                  Shaohan Huang and\n                  Shuming Ma and\n                  Yuwei Yin and\n                  Li Dong and\n                  Dongdong Zhang and\n                  Hongcheng Guo and\n                  Zhoujun Li and\n                  Furu Wei},\n  editor       = {Yoav Goldberg and\n                  Zornitsa Kozareva and\n                  Yue Zhang},\n  title        = {{CROP:} Zero-shot Cross-lingual Named Entity Recognition with Multilingual\n                  Labeled Sequence Translation},\n  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}\n                  2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},\n  pages        = {486--496},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2022},\n  url          = {https://doi.org/10.18653/v1/2022.findings-emnlp.34},\n  doi          = {10.18653/V1/2022.FINDINGS-EMNLP.34},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/emnlp/YangHMY0ZGLW22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Snapshot-Guided Domain Adaptation for ELECTRA.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; Liu, J.; Zhan, Y.; Sun, H.; Wei, F.; Deng, D.; and Zhang, Q.\n\n\n \n\n\n\n In Goldberg, Y.; Kozareva, Z.; and Zhang, Y., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 2226–2232, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Snapshot-GuidedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/ChengHLZ0WDZ22,\n  author       = {Daixuan Cheng and\n                  Shaohan Huang and\n                  Jianfeng Liu and\n                  Yuefeng Zhan and\n                  Hao Sun and\n                  Furu Wei and\n                  Denvy Deng and\n                  Qi Zhang},\n  editor       = {Yoav Goldberg and\n                  Zornitsa Kozareva and\n                  Yue Zhang},\n  title        = {Snapshot-Guided Domain Adaptation for {ELECTRA}},\n  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}\n                  2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},\n  pages        = {2226--2232},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2022},\n  url          = {https://doi.org/10.18653/v1/2022.findings-emnlp.163},\n  doi          = {10.18653/V1/2022.FINDINGS-EMNLP.163},\n  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/emnlp/ChengHLZ0WDZ22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n PromptBERT: Improving BERT Sentence Embeddings with Prompts.\n \n \n \n \n\n\n \n Jiang, T.; Jiao, J.; Huang, S.; Zhang, Z.; Wang, D.; Zhuang, F.; Wei, F.; Huang, H.; Deng, D.; and Zhang, Q.\n\n\n \n\n\n\n In Goldberg, Y.; Kozareva, Z.; and Zhang, Y., editor(s), Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 8826–8837, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"PromptBERT:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/JiangJHZWZWHDZ22,\n  author       = {Ting Jiang and\n                  Jian Jiao and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Deqing Wang and\n                  Fuzhen Zhuang and\n                  Furu Wei and\n                  Haizhen Huang and\n                  Denvy Deng and\n                  Qi Zhang},\n  editor       = {Yoav Goldberg and\n                  Zornitsa Kozareva and\n                  Yue Zhang},\n  title        = {PromptBERT: Improving {BERT} Sentence Embeddings with Prompts},\n  booktitle    = {Proceedings of the 2022 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates,\n                  December 7-11, 2022},\n  pages        = {8826--8837},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2022},\n  url          = {https://doi.org/10.18653/v1/2022.emnlp-main.603},\n  doi          = {10.18653/V1/2022.EMNLP-MAIN.603},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/emnlp/JiangJHZWZWHDZ22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning Music Sequence Representation From Text Supervision.\n \n \n \n \n\n\n \n Chen, T.; Xie, Y.; Zhang, S.; Huang, S.; Zhou, H.; and Li, J.\n\n\n \n\n\n\n In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022, pages 4583–4587, 2022. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/icassp/ChenXZHZL22,\n  author       = {Tianyu Chen and\n                  Yuan Xie and\n                  Shuai Zhang and\n                  Shaohan Huang and\n                  Haoyi Zhou and\n                  Jianxin Li},\n  title        = {Learning Music Sequence Representation From Text Supervision},\n  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,\n                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},\n  pages        = {4583--4587},\n  publisher    = {{IEEE}},\n  year         = {2022},\n  url          = {https://doi.org/10.1109/ICASSP43922.2022.9746131},\n  doi          = {10.1109/ICASSP43922.2022.9746131},\n  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/icassp/ChenXZHZL22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n On the Representation Collapse of Sparse Mixture of Experts.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Huang, S.; Dai, D.; Ma, S.; Patra, B.; Singhal, S.; Bajaj, P.; Song, X.; Mao, X.; Huang, H.; and Wei, F.\n\n\n \n\n\n\n In Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; and Oh, A., editor(s), Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022. \n \n\n\n\n
\n\n\n\n \n \n \"OnPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/Chi0HDMPSBSMHW22,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Shaohan Huang and\n                  Damai Dai and\n                  Shuming Ma and\n                  Barun Patra and\n                  Saksham Singhal and\n                  Payal Bajaj and\n                  Xia Song and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Furu Wei},\n  editor       = {Sanmi Koyejo and\n                  S. Mohamed and\n                  A. Agarwal and\n                  Danielle Belgrave and\n                  K. Cho and\n                  A. Oh},\n  title        = {On the Representation Collapse of Sparse Mixture of Experts},\n  booktitle    = {Advances in Neural Information Processing Systems 35: Annual Conference\n                  on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,\n                  LA, USA, November 28 - December 9, 2022},\n  year         = {2022},\n  url          = {http://papers.nips.cc/paper\\_files/paper/2022/hash/df4f371f1f89ec8ba5014b3310578048-Abstract-Conference.html},\n  timestamp    = {Mon, 08 Jan 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/nips/Chi0HDMPSBSMHW22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Kformer: Knowledge Injection in Transformer Feed-Forward Layers.\n \n \n \n \n\n\n \n Yao, Y.; Huang, S.; Dong, L.; Wei, F.; Chen, H.; and Zhang, N.\n\n\n \n\n\n\n In Lu, W.; Huang, S.; Hong, Y.; and Zhou, X., editor(s), Natural Language Processing and Chinese Computing - 11th CCF International Conference, NLPCC 2022, Guilin, China, September 24-25, 2022, Proceedings, Part I, volume 13551, of Lecture Notes in Computer Science, pages 131–143, 2022. Springer\n \n\n\n\n
\n\n\n\n \n \n \"Kformer:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nlpcc/YaoHDWCZ22,\n  author       = {Yunzhi Yao and\n                  Shaohan Huang and\n                  Li Dong and\n                  Furu Wei and\n                  Huajun Chen and\n                  Ningyu Zhang},\n  editor       = {Wei Lu and\n                  Shujian Huang and\n                  Yu Hong and\n                  Xiabing Zhou},\n  title        = {Kformer: Knowledge Injection in Transformer Feed-Forward Layers},\n  booktitle    = {Natural Language Processing and Chinese Computing - 11th {CCF} International\n                  Conference, {NLPCC} 2022, Guilin, China, September 24-25, 2022, Proceedings,\n                  Part {I}},\n  series       = {Lecture Notes in Computer Science},\n  volume       = {13551},\n  pages        = {131--143},\n  publisher    = {Springer},\n  year         = {2022},\n  url          = {https://doi.org/10.1007/978-3-031-17120-8\\_11},\n  doi          = {10.1007/978-3-031-17120-8\\_11},\n  timestamp    = {Tue, 27 Dec 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/nlpcc/YaoHDWCZ22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Adanomaly: Adaptive Anomaly Detection for System Logs with Adversarial Learning.\n \n \n \n \n\n\n \n Qi, J.; Luan, Z.; Huang, S.; Wang, Y.; Fung, C. J.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n In 2022 IEEE/IFIP Network Operations and Management Symposium, NOMS 2022, Budapest, Hungary, April 25-29, 2022, pages 1–5, 2022. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"Adanomaly:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/noms/QiLHWFYQ22,\n  author       = {Jiaxing Qi and\n                  Zhongzhi Luan and\n                  Shaohan Huang and\n                  Yukun Wang and\n                  Carol J. Fung and\n                  Hailong Yang and\n                  Depei Qian},\n  title        = {Adanomaly: Adaptive Anomaly Detection for System Logs with Adversarial\n                  Learning},\n  booktitle    = {2022 {IEEE/IFIP} Network Operations and Management Symposium, {NOMS}\n                  2022, Budapest, Hungary, April 25-29, 2022},\n  pages        = {1--5},\n  publisher    = {{IEEE}},\n  year         = {2022},\n  url          = {https://doi.org/10.1109/NOMS54207.2022.9789917},\n  doi          = {10.1109/NOMS54207.2022.9789917},\n  timestamp    = {Wed, 15 Jun 2022 16:45:18 +0200},\n  biburl       = {https://dblp.org/rec/conf/noms/QiLHWFYQ22.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n PromptBERT: Improving BERT Sentence Embeddings with Prompts.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Zhang, Z.; Wang, D.; Zhuang, F.; Wei, F.; Huang, H.; Zhang, L.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2201.04337. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"PromptBERT:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2201-04337,\n  author       = {Ting Jiang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Deqing Wang and\n                  Fuzhen Zhuang and\n                  Furu Wei and\n                  Haizhen Huang and\n                  Liangjie Zhang and\n                  Qi Zhang},\n  title        = {PromptBERT: Improving {BERT} Sentence Embeddings with Prompts},\n  journal      = {CoRR},\n  volume       = {abs/2201.04337},\n  year         = {2022},\n  url          = {https://arxiv.org/abs/2201.04337},\n  eprinttype    = {arXiv},\n  eprint       = {2201.04337},\n  timestamp    = {Thu, 20 Jan 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2201-04337.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Kformer: Knowledge Injection in Transformer Feed-Forward Layers.\n \n \n \n \n\n\n \n Yao, Y.; Huang, S.; Zhang, N.; Dong, L.; Wei, F.; and Chen, H.\n\n\n \n\n\n\n CoRR, abs/2201.05742. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"Kformer:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2201-05742,\n  author       = {Yunzhi Yao and\n                  Shaohan Huang and\n                  Ningyu Zhang and\n                  Li Dong and\n                  Furu Wei and\n                  Huajun Chen},\n  title        = {Kformer: Knowledge Injection in Transformer Feed-Forward Layers},\n  journal      = {CoRR},\n  volume       = {abs/2201.05742},\n  year         = {2022},\n  url          = {https://arxiv.org/abs/2201.05742},\n  eprinttype    = {arXiv},\n  eprint       = {2201.05742},\n  timestamp    = {Tue, 27 Dec 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2201-05742.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DeepNet: Scaling Transformers to 1, 000 Layers.\n \n \n \n \n\n\n \n Wang, H.; Ma, S.; Dong, L.; Huang, S.; Zhang, D.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2203.00555. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"DeepNet:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2203-00555,\n  author       = {Hongyu Wang and\n                  Shuming Ma and\n                  Li Dong and\n                  Shaohan Huang and\n                  Dongdong Zhang and\n                  Furu Wei},\n  title        = {DeepNet: Scaling Transformers to 1, 000 Layers},\n  journal      = {CoRR},\n  volume       = {abs/2203.00555},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2203.00555},\n  doi          = {10.48550/ARXIV.2203.00555},\n  eprinttype    = {arXiv},\n  eprint       = {2203.00555},\n  timestamp    = {Tue, 20 Dec 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2203-00555.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n On the Representation Collapse of Sparse Mixture of Experts.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Huang, S.; Dai, D.; Ma, S.; Patra, B.; Singhal, S.; Bajaj, P.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2204.09179. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"OnPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2204-09179,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Shaohan Huang and\n                  Damai Dai and\n                  Shuming Ma and\n                  Barun Patra and\n                  Saksham Singhal and\n                  Payal Bajaj and\n                  Xia Song and\n                  Furu Wei},\n  title        = {On the Representation Collapse of Sparse Mixture of Experts},\n  journal      = {CoRR},\n  volume       = {abs/2204.09179},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2204.09179},\n  doi          = {10.48550/ARXIV.2204.09179},\n  eprinttype    = {arXiv},\n  eprint       = {2204.09179},\n  timestamp    = {Mon, 25 Apr 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2204-09179.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption.\n \n \n \n \n\n\n \n Chen, T.; Bao, H.; Huang, S.; Dong, L.; Jiao, B.; Jiang, D.; Zhou, H.; Li, J.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2206.00216. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"THE-X:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2206-00216,\n  author       = {Tianyu Chen and\n                  Hangbo Bao and\n                  Shaohan Huang and\n                  Li Dong and\n                  Binxing Jiao and\n                  Daxin Jiang and\n                  Haoyi Zhou and\n                  Jianxin Li and\n                  Furu Wei},\n  title        = {{THE-X:} Privacy-Preserving Transformer Inference with Homomorphic\n                  Encryption},\n  journal      = {CoRR},\n  volume       = {abs/2206.00216},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2206.00216},\n  doi          = {10.48550/ARXIV.2206.00216},\n  eprinttype    = {arXiv},\n  eprint       = {2206.00216},\n  timestamp    = {Mon, 01 May 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-00216.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Task-Specific Expert Pruning for Sparse Mixture-of-Experts.\n \n \n \n \n\n\n \n Chen, T.; Huang, S.; Xie, Y.; Jiao, B.; Jiang, D.; Zhou, H.; Li, J.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2206.00277. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"Task-SpecificPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2206-00277,\n  author       = {Tianyu Chen and\n                  Shaohan Huang and\n                  Yuan Xie and\n                  Binxing Jiao and\n                  Daxin Jiang and\n                  Haoyi Zhou and\n                  Jianxin Li and\n                  Furu Wei},\n  title        = {Task-Specific Expert Pruning for Sparse Mixture-of-Experts},\n  journal      = {CoRR},\n  volume       = {abs/2206.00277},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2206.00277},\n  doi          = {10.48550/ARXIV.2206.00277},\n  eprinttype    = {arXiv},\n  eprint       = {2206.00277},\n  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-00277.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Language Models are General-Purpose Interfaces.\n \n \n \n \n\n\n \n Hao, Y.; Song, H.; Dong, L.; Huang, S.; Chi, Z.; Wang, W.; Ma, S.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2206.06336. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"LanguagePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2206-06336,\n  author       = {Yaru Hao and\n                  Haoyu Song and\n                  Li Dong and\n                  Shaohan Huang and\n                  Zewen Chi and\n                  Wenhui Wang and\n                  Shuming Ma and\n                  Furu Wei},\n  title        = {Language Models are General-Purpose Interfaces},\n  journal      = {CoRR},\n  volume       = {abs/2206.06336},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2206.06336},\n  doi          = {10.48550/ARXIV.2206.06336},\n  eprinttype    = {arXiv},\n  eprint       = {2206.06336},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-06336.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MoEC: Mixture of Expert Clusters.\n \n \n \n \n\n\n \n Xie, Y.; Huang, S.; Chen, T.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2207.09094. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"MoEC:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2207-09094,\n  author       = {Yuan Xie and\n                  Shaohan Huang and\n                  Tianyu Chen and\n                  Furu Wei},\n  title        = {MoEC: Mixture of Expert Clusters},\n  journal      = {CoRR},\n  volume       = {abs/2207.09094},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2207.09094},\n  doi          = {10.48550/ARXIV.2207.09094},\n  eprinttype    = {arXiv},\n  eprint       = {2207.09094},\n  timestamp    = {Mon, 25 Jul 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2207-09094.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Foundation Transformers.\n \n \n \n \n\n\n \n Wang, H.; Ma, S.; Huang, S.; Dong, L.; Wang, W.; Peng, Z.; Wu, Y.; Bajaj, P.; Singhal, S.; Benhaim, A.; Patra, B.; Liu, Z.; Chaudhary, V.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2210.06423. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"FoundationPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2210-06423,\n  author       = {Hongyu Wang and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Li Dong and\n                  Wenhui Wang and\n                  Zhiliang Peng and\n                  Yu Wu and\n                  Payal Bajaj and\n                  Saksham Singhal and\n                  Alon Benhaim and\n                  Barun Patra and\n                  Zhun Liu and\n                  Vishrav Chaudhary and\n                  Xia Song and\n                  Furu Wei},\n  title        = {Foundation Transformers},\n  journal      = {CoRR},\n  volume       = {abs/2210.06423},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2210.06423},\n  doi          = {10.48550/ARXIV.2210.06423},\n  eprinttype    = {arXiv},\n  eprint       = {2210.06423},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-06423.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation.\n \n \n \n \n\n\n \n Yang, J.; Huang, S.; Ma, S.; Yin, Y.; Dong, L.; Zhang, D.; Guo, H.; Li, Z.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2210.07022. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"CROP:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2210-07022,\n  author       = {Jian Yang and\n                  Shaohan Huang and\n                  Shuming Ma and\n                  Yuwei Yin and\n                  Li Dong and\n                  Dongdong Zhang and\n                  Hongcheng Guo and\n                  Zhoujun Li and\n                  Furu Wei},\n  title        = {{CROP:} Zero-shot Cross-lingual Named Entity Recognition with Multilingual\n                  Labeled Sequence Translation},\n  journal      = {CoRR},\n  volume       = {abs/2210.07022},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2210.07022},\n  doi          = {10.48550/ARXIV.2210.07022},\n  eprinttype    = {arXiv},\n  eprint       = {2210.07022},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-07022.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning.\n \n \n \n \n\n\n \n Patra, B.; Singhal, S.; Huang, S.; Chi, Z.; Dong, L.; Wei, F.; Chaudhary, V.; and Song, X.\n\n\n \n\n\n\n CoRR, abs/2210.14867. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"BeyondPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2210-14867,\n  author       = {Barun Patra and\n                  Saksham Singhal and\n                  Shaohan Huang and\n                  Zewen Chi and\n                  Li Dong and\n                  Furu Wei and\n                  Vishrav Chaudhary and\n                  Xia Song},\n  title        = {Beyond English-Centric Bitexts for Better Multilingual Language Representation\n                  Learning},\n  journal      = {CoRR},\n  volume       = {abs/2210.14867},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2210.14867},\n  doi          = {10.48550/ARXIV.2210.14867},\n  eprinttype    = {arXiv},\n  eprint       = {2210.14867},\n  timestamp    = {Wed, 02 Nov 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-14867.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n TorchScale: Transformers at Scale.\n \n \n \n \n\n\n \n Ma, S.; Wang, H.; Huang, S.; Wang, W.; Chi, Z.; Dong, L.; Benhaim, A.; Patra, B.; Chaudhary, V.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2211.13184. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"TorchScale:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2211-13184,\n  author       = {Shuming Ma and\n                  Hongyu Wang and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Zewen Chi and\n                  Li Dong and\n                  Alon Benhaim and\n                  Barun Patra and\n                  Vishrav Chaudhary and\n                  Xia Song and\n                  Furu Wei},\n  title        = {TorchScale: Transformers at Scale},\n  journal      = {CoRR},\n  volume       = {abs/2211.13184},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2211.13184},\n  doi          = {10.48550/ARXIV.2211.13184},\n  eprinttype    = {arXiv},\n  eprint       = {2211.13184},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2211-13184.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator.\n \n \n \n \n\n\n \n Yang, J.; Ma, S.; Dong, L.; Huang, S.; Huang, H.; Yin, Y.; Zhang, D.; Yang, L.; Li, Z.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2212.10218. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"GanLM:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2212-10218,\n  author       = {Jian Yang and\n                  Shuming Ma and\n                  Li Dong and\n                  Shaohan Huang and\n                  Haoyang Huang and\n                  Yuwei Yin and\n                  Dongdong Zhang and\n                  Liqun Yang and\n                  Zhoujun Li and\n                  Furu Wei},\n  title        = {GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator},\n  journal      = {CoRR},\n  volume       = {abs/2212.10218},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2212.10218},\n  doi          = {10.48550/ARXIV.2212.10218},\n  eprinttype    = {arXiv},\n  eprint       = {2212.10218},\n  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-10218.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Length-Extrapolatable Transformer.\n \n \n \n \n\n\n \n Sun, Y.; Dong, L.; Patra, B.; Ma, S.; Huang, S.; Benhaim, A.; Chaudhary, V.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2212.10554. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2212-10554,\n  author       = {Yutao Sun and\n                  Li Dong and\n                  Barun Patra and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Alon Benhaim and\n                  Vishrav Chaudhary and\n                  Xia Song and\n                  Furu Wei},\n  title        = {A Length-Extrapolatable Transformer},\n  journal      = {CoRR},\n  volume       = {abs/2212.10554},\n  year         = {2022},\n  url          = {https://doi.org/10.48550/arXiv.2212.10554},\n  doi          = {10.48550/ARXIV.2212.10554},\n  eprinttype    = {arXiv},\n  eprint       = {2212.10554},\n  timestamp    = {Wed, 04 Jan 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-10554.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (17)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains.\n \n \n \n \n\n\n \n Yao, Y.; Huang, S.; Wang, W.; Dong, L.; and Wei, F.\n\n\n \n\n\n\n In Zong, C.; Xia, F.; Li, W.; and Navigli, R., editor(s), Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021, volume ACL/IJCNLP 2021, of Findings of ACL, pages 460–470, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Adapt-and-Distill:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/YaoHWDW21,\n  author       = {Yunzhi Yao and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Li Dong and\n                  Furu Wei},\n  editor       = {Chengqing Zong and\n                  Fei Xia and\n                  Wenjie Li and\n                  Roberto Navigli},\n  title        = {Adapt-and-Distill: Developing Small, Fast and Effective Pretrained\n                  Language Models for Domains},\n  booktitle    = {Findings of the Association for Computational Linguistics: {ACL/IJCNLP}\n                  2021, Online Event, August 1-6, 2021},\n  series       = {Findings of {ACL}},\n  volume       = {{ACL/IJCNLP} 2021},\n  pages        = {460--470},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.findings-acl.40},\n  doi          = {10.18653/V1/2021.FINDINGS-ACL.40},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/YaoHWDW21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers.\n \n \n \n \n\n\n \n Wang, W.; Bao, H.; Huang, S.; Dong, L.; and Wei, F.\n\n\n \n\n\n\n In Zong, C.; Xia, F.; Li, W.; and Navigli, R., editor(s), Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021, volume ACL/IJCNLP 2021, of Findings of ACL, pages 2140–2151, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"MiniLMv2:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/WangBHDW21,\n  author       = {Wenhui Wang and\n                  Hangbo Bao and\n                  Shaohan Huang and\n                  Li Dong and\n                  Furu Wei},\n  editor       = {Chengqing Zong and\n                  Fei Xia and\n                  Wenjie Li and\n                  Roberto Navigli},\n  title        = {MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing\n                  Pretrained Transformers},\n  booktitle    = {Findings of the Association for Computational Linguistics: {ACL/IJCNLP}\n                  2021, Online Event, August 1-6, 2021},\n  series       = {Findings of {ACL}},\n  volume       = {{ACL/IJCNLP} 2021},\n  pages        = {2140--2151},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.findings-acl.188},\n  doi          = {10.18653/V1/2021.FINDINGS-ACL.188},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/WangBHDW21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Consistency Regularization for Cross-Lingual Fine-Tuning.\n \n \n \n \n\n\n \n Zheng, B.; Dong, L.; Huang, S.; Wang, W.; Chi, Z.; Singhal, S.; Che, W.; Liu, T.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Zong, C.; Xia, F.; Li, W.; and Navigli, R., editor(s), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pages 3403–3417, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ConsistencyPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/Zheng0HWCSC0SW20,\n  author       = {Bo Zheng and\n                  Li Dong and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Zewen Chi and\n                  Saksham Singhal and\n                  Wanxiang Che and\n                  Ting Liu and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Chengqing Zong and\n                  Fei Xia and\n                  Wenjie Li and\n                  Roberto Navigli},\n  title        = {Consistency Regularization for Cross-Lingual Fine-Tuning},\n  booktitle    = {Proceedings of the 59th Annual Meeting of the Association for Computational\n                  Linguistics and the 11th International Joint Conference on Natural\n                  Language Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), Virtual\n                  Event, August 1-6, 2021},\n  pages        = {3403--3417},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.acl-long.264},\n  doi          = {10.18653/V1/2021.ACL-LONG.264},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/Zheng0HWCSC0SW20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Zheng, B.; Huang, S.; Mao, X.; Huang, H.; and Wei, F.\n\n\n \n\n\n\n In Zong, C.; Xia, F.; Li, W.; and Navigli, R., editor(s), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pages 3418–3430, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/Chi0ZHMHW20,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Bo Zheng and\n                  Shaohan Huang and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Furu Wei},\n  editor       = {Chengqing Zong and\n                  Fei Xia and\n                  Wenjie Li and\n                  Roberto Navigli},\n  title        = {Improving Pretrained Cross-Lingual Language Models via Self-Labeled\n                  Word Alignment},\n  booktitle    = {Proceedings of the 59th Annual Meeting of the Association for Computational\n                  Linguistics and the 11th International Joint Conference on Natural\n                  Language Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), Virtual\n                  Event, August 1-6, 2021},\n  pages        = {3418--3430},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.acl-long.265},\n  doi          = {10.18653/V1/2021.ACL-LONG.265},\n  timestamp    = {Mon, 09 Aug 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/Chi0ZHMHW20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n PriPro: Towards Effective Privacy Protection on Edge-Cloud System running DNN Inference.\n \n \n \n \n\n\n \n Gao, R.; Yang, H.; Huang, S.; Dun, M.; Li, M.; Luan, Z.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In Lefèvre, L.; Patterson, S.; Lee, Y. C.; Shen, H.; Ilager, S.; Goudarzi, M.; Toosi, A. N.; and Buyya, R., editor(s), 21st IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2021, Melbourne, Australia, May 10-13, 2021, pages 334–343, 2021. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"PriPro:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/ccgrid/GaoYHDLLLQ21,\n  author       = {Ruiyuan Gao and\n                  Hailong Yang and\n                  Shaohan Huang and\n                  Ming Dun and\n                  Mingzhen Li and\n                  Zerong Luan and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  editor       = {Laurent Lef{\\`{e}}vre and\n                  Stacy Patterson and\n                  Young Choon Lee and\n                  Haiying Shen and\n                  Shashikant Ilager and\n                  Mohammad Goudarzi and\n                  Adel Nadjaran Toosi and\n                  Rajkumar Buyya},\n  title        = {PriPro: Towards Effective Privacy Protection on Edge-Cloud System\n                  running {DNN} Inference},\n  booktitle    = {21st {IEEE/ACM} International Symposium on Cluster, Cloud and Internet\n                  Computing, CCGrid 2021, Melbourne, Australia, May 10-13, 2021},\n  pages        = {334--343},\n  publisher    = {{IEEE}},\n  year         = {2021},\n  url          = {https://doi.org/10.1109/CCGrid51090.2021.00043},\n  doi          = {10.1109/CCGRID51090.2021.00043},\n  timestamp    = {Thu, 02 Sep 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/ccgrid/GaoYHDLLLQ21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Ma, S.; Huang, S.; Singhal, S.; Mao, X.; Huang, H.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Moens, M.; Huang, X.; Specia, L.; and Yih, S. W., editor(s), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pages 1671–1683, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"mT6:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/ChiDMHSMHSW21,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Saksham Singhal and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Marie{-}Francine Moens and\n                  Xuanjing Huang and\n                  Lucia Specia and\n                  Scott Wen{-}tau Yih},\n  title        = {mT6: Multilingual Pretrained Text-to-Text Transformer with Translation\n                  Pairs},\n  booktitle    = {Proceedings of the 2021 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican\n                  Republic, 7-11 November, 2021},\n  pages        = {1671--1683},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.emnlp-main.125},\n  doi          = {10.18653/V1/2021.EMNLP-MAIN.125},\n  timestamp    = {Fri, 16 Feb 2024 08:27:36 +0100},\n  biburl       = {https://dblp.org/rec/conf/emnlp/ChiDMHSMHSW21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training.\n \n \n \n \n\n\n \n Zheng, B.; Dong, L.; Huang, S.; Singhal, S.; Che, W.; Liu, T.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Moens, M.; Huang, X.; Specia, L.; and Yih, S. W., editor(s), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pages 3203–3215, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AllocatingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/ZhengDHSCLSW21,\n  author       = {Bo Zheng and\n                  Li Dong and\n                  Shaohan Huang and\n                  Saksham Singhal and\n                  Wanxiang Che and\n                  Ting Liu and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Marie{-}Francine Moens and\n                  Xuanjing Huang and\n                  Lucia Specia and\n                  Scott Wen{-}tau Yih},\n  title        = {Allocating Large Vocabulary Capacity for Cross-Lingual Language Model\n                  Pre-Training},\n  booktitle    = {Proceedings of the 2021 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican\n                  Republic, 7-11 November, 2021},\n  pages        = {3203--3215},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://doi.org/10.18653/v1/2021.emnlp-main.257},\n  doi          = {10.18653/V1/2021.EMNLP-MAIN.257},\n  timestamp    = {Wed, 16 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/emnlp/ZhengDHSCLSW21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task.\n \n \n \n \n\n\n \n Yang, J.; Ma, S.; Huang, H.; Zhang, D.; Dong, L.; Huang, S.; Muzio, A.; Singhal, S.; Hassan, H.; Song, X.; and Wei, F.\n\n\n \n\n\n\n In Barrault, L.; Bojar, O.; Bougares, F.; Chatterjee, R.; Costa-jussà, M. R.; Federmann, C.; Fishel, M.; Fraser, A.; Freitag, M.; Graham, Y.; Grundkiewicz, R.; Guzman, P.; Haddow, B.; Huck, M.; Jimeno-Yepes, A.; Koehn, P.; Kocmi, T.; Martins, A.; Morishita, M.; and Monz, C., editor(s), Proceedings of the Sixth Conference on Machine Translation, WMT@EMNLP 2021, Online Event, November 10-11, 2021, pages 446–455, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"MultilingualPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/wmt/YangMH00HMSHSW21,\n  author       = {Jian Yang and\n                  Shuming Ma and\n                  Haoyang Huang and\n                  Dongdong Zhang and\n                  Li Dong and\n                  Shaohan Huang and\n                  Alexandre Muzio and\n                  Saksham Singhal and\n                  Hany Hassan and\n                  Xia Song and\n                  Furu Wei},\n  editor       = {Lo{\\"{\\i}}c Barrault and\n                  Ondrej Bojar and\n                  Fethi Bougares and\n                  Rajen Chatterjee and\n                  Marta R. Costa{-}juss{\\`{a}} and\n                  Christian Federmann and\n                  Mark Fishel and\n                  Alexander Fraser and\n                  Markus Freitag and\n                  Yvette Graham and\n                  Roman Grundkiewicz and\n                  Paco Guzman and\n                  Barry Haddow and\n                  Matthias Huck and\n                  Antonio Jimeno{-}Yepes and\n                  Philipp Koehn and\n                  Tom Kocmi and\n                  Andr{\\'{e}} Martins and\n                  Makoto Morishita and\n                  Christof Monz},\n  title        = {Multilingual Machine Translation Systems from Microsoft for {WMT21}\n                  Shared Task},\n  booktitle    = {Proceedings of the Sixth Conference on Machine Translation, WMT@EMNLP\n                  2021, Online Event, November 10-11, 2021},\n  pages        = {446--455},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2021},\n  url          = {https://aclanthology.org/2021.wmt-1.54},\n  timestamp    = {Wed, 07 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/wmt/YangMH00HMSHSW21.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Ma, S.; Huang, S.; Mao, X.; Huang, H.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2104.08692. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"mT6:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2104-08692,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Shuming Ma and\n                  Shaohan Huang and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Furu Wei},\n  title        = {mT6: Multilingual Pretrained Text-to-Text Transformer with Translation\n                  Pairs},\n  journal      = {CoRR},\n  volume       = {abs/2104.08692},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2104.08692},\n  eprinttype    = {arXiv},\n  eprint       = {2104.08692},\n  timestamp    = {Mon, 26 Apr 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-08692.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment.\n \n \n \n \n\n\n \n Chi, Z.; Dong, L.; Zheng, B.; Huang, S.; Mao, X.; Huang, H.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2106.06381. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2106-06381,\n  author       = {Zewen Chi and\n                  Li Dong and\n                  Bo Zheng and\n                  Shaohan Huang and\n                  Xian{-}Ling Mao and\n                  Heyan Huang and\n                  Furu Wei},\n  title        = {Improving Pretrained Cross-Lingual Language Models via Self-Labeled\n                  Word Alignment},\n  journal      = {CoRR},\n  volume       = {abs/2106.06381},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2106.06381},\n  eprinttype    = {arXiv},\n  eprint       = {2106.06381},\n  timestamp    = {Tue, 15 Jun 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-06381.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Consistency Regularization for Cross-Lingual Fine-Tuning.\n \n \n \n \n\n\n \n Zheng, B.; Dong, L.; Huang, S.; Wang, W.; Chi, Z.; Singhal, S.; Che, W.; Liu, T.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2106.08226. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"ConsistencyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2106-08226,\n  author       = {Bo Zheng and\n                  Li Dong and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Zewen Chi and\n                  Saksham Singhal and\n                  Wanxiang Che and\n                  Ting Liu and\n                  Xia Song and\n                  Furu Wei},\n  title        = {Consistency Regularization for Cross-Lingual Fine-Tuning},\n  journal      = {CoRR},\n  volume       = {abs/2106.08226},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2106.08226},\n  eprinttype    = {arXiv},\n  eprint       = {2106.08226},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-08226.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains.\n \n \n \n \n\n\n \n Yao, Y.; Huang, S.; Wang, W.; Dong, L.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2106.13474. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"Adapt-and-Distill:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2106-13474,\n  author       = {Yunzhi Yao and\n                  Shaohan Huang and\n                  Wenhui Wang and\n                  Li Dong and\n                  Furu Wei},\n  title        = {Adapt-and-Distill: Developing Small, Fast and Effective Pretrained\n                  Language Models for Domains},\n  journal      = {CoRR},\n  volume       = {abs/2106.13474},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2106.13474},\n  eprinttype    = {arXiv},\n  eprint       = {2106.13474},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-13474.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders.\n \n \n \n \n\n\n \n Ma, S.; Dong, L.; Huang, S.; Zhang, D.; Muzio, A.; Singhal, S.; Awadalla, H. H.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2106.13736. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"DeltaLM:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2106-13736,\n  author       = {Shuming Ma and\n                  Li Dong and\n                  Shaohan Huang and\n                  Dongdong Zhang and\n                  Alexandre Muzio and\n                  Saksham Singhal and\n                  Hany Hassan Awadalla and\n                  Xia Song and\n                  Furu Wei},\n  title        = {DeltaLM: Encoder-Decoder Pre-training for Language Generation and\n                  Translation by Augmenting Pretrained Multilingual Encoders},\n  journal      = {CoRR},\n  volume       = {abs/2106.13736},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2106.13736},\n  eprinttype    = {arXiv},\n  eprint       = {2106.13736},\n  timestamp    = {Wed, 30 Jun 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-13736.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n XLM-E: Cross-lingual Language Model Pre-training via ELECTRA.\n \n \n \n \n\n\n \n Chi, Z.; Huang, S.; Dong, L.; Ma, S.; Singhal, S.; Bajaj, P.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2106.16138. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"XLM-E:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2106-16138,\n  author       = {Zewen Chi and\n                  Shaohan Huang and\n                  Li Dong and\n                  Shuming Ma and\n                  Saksham Singhal and\n                  Payal Bajaj and\n                  Xia Song and\n                  Furu Wei},\n  title        = {{XLM-E:} Cross-lingual Language Model Pre-training via {ELECTRA}},\n  journal      = {CoRR},\n  volume       = {abs/2106.16138},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2106.16138},\n  eprinttype    = {arXiv},\n  eprint       = {2106.16138},\n  timestamp    = {Mon, 05 Jul 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-16138.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training.\n \n \n \n \n\n\n \n Zheng, B.; Dong, L.; Huang, S.; Singhal, S.; Che, W.; Liu, T.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2109.07306. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"AllocatingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2109-07306,\n  author       = {Bo Zheng and\n                  Li Dong and\n                  Shaohan Huang and\n                  Saksham Singhal and\n                  Wanxiang Che and\n                  Ting Liu and\n                  Xia Song and\n                  Furu Wei},\n  title        = {Allocating Large Vocabulary Capacity for Cross-lingual Language Model\n                  Pre-training},\n  journal      = {CoRR},\n  volume       = {abs/2109.07306},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2109.07306},\n  eprinttype    = {arXiv},\n  eprint       = {2109.07306},\n  timestamp    = {Wed, 16 Aug 2023 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-07306.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Non-autoregressive Generation with Mixup Training.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Zhang, Z.; Wang, D.; Zhuang, F.; Wei, F.; Huang, H.; Zhang, L.; and Zhang, Q.\n\n\n \n\n\n\n CoRR, abs/2110.11115. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2110-11115,\n  author       = {Ting Jiang and\n                  Shaohan Huang and\n                  Zihan Zhang and\n                  Deqing Wang and\n                  Fuzhen Zhuang and\n                  Furu Wei and\n                  Haizhen Huang and\n                  Liangjie Zhang and\n                  Qi Zhang},\n  title        = {Improving Non-autoregressive Generation with Mixup Training},\n  journal      = {CoRR},\n  volume       = {abs/2110.11115},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2110.11115},\n  eprinttype    = {arXiv},\n  eprint       = {2110.11115},\n  timestamp    = {Thu, 28 Oct 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-11115.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task.\n \n \n \n \n\n\n \n Yang, J.; Ma, S.; Huang, H.; Zhang, D.; Dong, L.; Huang, S.; Muzio, A.; Singhal, S.; Awadalla, H. H.; Song, X.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2111.02086. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"MultilingualPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2111-02086,\n  author       = {Jian Yang and\n                  Shuming Ma and\n                  Haoyang Huang and\n                  Dongdong Zhang and\n                  Li Dong and\n                  Shaohan Huang and\n                  Alexandre Muzio and\n                  Saksham Singhal and\n                  Hany Hassan Awadalla and\n                  Xia Song and\n                  Furu Wei},\n  title        = {Multilingual Machine Translation Systems from Microsoft for {WMT21}\n                  Shared Task},\n  journal      = {CoRR},\n  volume       = {abs/2111.02086},\n  year         = {2021},\n  url          = {https://arxiv.org/abs/2111.02086},\n  eprinttype    = {arXiv},\n  eprint       = {2111.02086},\n  timestamp    = {Wed, 07 Feb 2024 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2111-02086.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (15)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A Joint Sentence Scoring and Selection Framework for Neural Extractive Document Summarization.\n \n \n \n \n\n\n \n Zhou, Q.; Yang, N.; Wei, F.; Huang, S.; Zhou, M.; and Zhao, T.\n\n\n \n\n\n\n IEEE ACM Trans. Audio Speech Lang. Process., 28: 671–681. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/taslp/ZhouYWHZZ20,\n  author       = {Qingyu Zhou and\n                  Nan Yang and\n                  Furu Wei and\n                  Shaohan Huang and\n                  Ming Zhou and\n                  Tiejun Zhao},\n  title        = {A Joint Sentence Scoring and Selection Framework for Neural Extractive\n                  Document Summarization},\n  journal      = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},\n  volume       = {28},\n  pages        = {671--681},\n  year         = {2020},\n  url          = {https://doi.org/10.1109/TASLP.2020.2964427},\n  doi          = {10.1109/TASLP.2020.2964427},\n  timestamp    = {Fri, 13 Mar 2020 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/taslp/ZhouYWHZZ20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n HitAnomaly: Hierarchical Transformers for Anomaly Detection in System Log.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; He, R.; Zhao, Y.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n IEEE Trans. Netw. Serv. Manag., 17(4): 2064–2076. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"HitAnomaly:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/tnsm/HuangLFHZYL20,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Rong He and\n                  Yining Zhao and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  title        = {HitAnomaly: Hierarchical Transformers for Anomaly Detection in System\n                  Log},\n  journal      = {{IEEE} Trans. Netw. Serv. Manag.},\n  volume       = {17},\n  number       = {4},\n  pages        = {2064--2076},\n  year         = {2020},\n  url          = {https://doi.org/10.1109/TNSM.2020.3034647},\n  doi          = {10.1109/TNSM.2020.3034647},\n  timestamp    = {Wed, 15 Jun 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/tnsm/HuangLFHZYL20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Transfer Log-based Anomaly Detection with Pseudo Labels.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; He, R.; Zhao, Y.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n In Zincir-Heywood, N.; Ulema, M.; Sayit, M.; Clayman, S.; Kim, M.; and Cetinkaya, C., editor(s), 16th International Conference on Network and Service Management, CNSM 2020, Izmir, Turkey, November 2-6, 2020, pages 1–5, 2020. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"TransferPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/cnsm/HuangLFHZYL20,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Rong He and\n                  Yining Zhao and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  editor       = {Nur Zincir{-}Heywood and\n                  Mehmet Ulema and\n                  M{\\"{u}}ge Sayit and\n                  Stuart Clayman and\n                  Myung{-}Sup Kim and\n                  Cihat Cetinkaya},\n  title        = {Transfer Log-based Anomaly Detection with Pseudo Labels},\n  booktitle    = {16th International Conference on Network and Service Management, {CNSM}\n                  2020, Izmir, Turkey, November 2-6, 2020},\n  pages        = {1--5},\n  publisher    = {{IEEE}},\n  year         = {2020},\n  url          = {https://doi.org/10.23919/CNSM50824.2020.9269069},\n  doi          = {10.23919/CNSM50824.2020.9269069},\n  timestamp    = {Fri, 08 Dec 2023 07:53:07 +0100},\n  biburl       = {https://dblp.org/rec/conf/cnsm/HuangLFHZYL20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DocBank: A Benchmark Dataset for Document Layout Analysis.\n \n \n \n \n\n\n \n Li, M.; Xu, Y.; Cui, L.; Huang, S.; Wei, F.; Li, Z.; and Zhou, M.\n\n\n \n\n\n\n In Scott, D.; Bel, N.; and Zong, C., editor(s), Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, pages 949–960, 2020. International Committee on Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"DocBank:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/coling/LiXCHWLZ20,\n  author       = {Minghao Li and\n                  Yiheng Xu and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Zhoujun Li and\n                  Ming Zhou},\n  editor       = {Donia Scott and\n                  N{\\'{u}}ria Bel and\n                  Chengqing Zong},\n  title        = {DocBank: {A} Benchmark Dataset for Document Layout Analysis},\n  booktitle    = {Proceedings of the 28th International Conference on Computational\n                  Linguistics, {COLING} 2020, Barcelona, Spain (Online), December 8-13,\n                  2020},\n  pages        = {949--960},\n  publisher    = {International Committee on Computational Linguistics},\n  year         = {2020},\n  url          = {https://doi.org/10.18653/v1/2020.coling-main.82},\n  doi          = {10.18653/V1/2020.COLING-MAIN.82},\n  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/coling/LiXCHWLZ20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Unsupervised Fine-tuning for Text Clustering.\n \n \n \n \n\n\n \n Huang, S.; Wei, F.; Cui, L.; Zhang, X.; and Zhou, M.\n\n\n \n\n\n\n In Scott, D.; Bel, N.; and Zong, C., editor(s), Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, pages 5530–5534, 2020. International Committee on Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"UnsupervisedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/coling/HuangWCZZ20,\n  author       = {Shaohan Huang and\n                  Furu Wei and\n                  Lei Cui and\n                  Xingxing Zhang and\n                  Ming Zhou},\n  editor       = {Donia Scott and\n                  N{\\'{u}}ria Bel and\n                  Chengqing Zong},\n  title        = {Unsupervised Fine-tuning for Text Clustering},\n  booktitle    = {Proceedings of the 28th International Conference on Computational\n                  Linguistics, {COLING} 2020, Barcelona, Spain (Online), December 8-13,\n                  2020},\n  pages        = {5530--5534},\n  publisher    = {International Committee on Computational Linguistics},\n  year         = {2020},\n  url          = {https://doi.org/10.18653/v1/2020.coling-main.482},\n  doi          = {10.18653/V1/2020.COLING-MAIN.482},\n  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/coling/HuangWCZZ20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph.\n \n \n \n \n\n\n \n Ji, H.; Ke, P.; Huang, S.; Wei, F.; Zhu, X.; and Huang, M.\n\n\n \n\n\n\n In Webber, B.; Cohn, T.; He, Y.; and Liu, Y., editor(s), Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 725–736, 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"LanguagePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/JiKHWZH20,\n  author       = {Haozhe Ji and\n                  Pei Ke and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Xiaoyan Zhu and\n                  Minlie Huang},\n  editor       = {Bonnie Webber and\n                  Trevor Cohn and\n                  Yulan He and\n                  Yang Liu},\n  title        = {Language Generation with Multi-Hop Reasoning on Commonsense Knowledge\n                  Graph},\n  booktitle    = {Proceedings of the 2020 Conference on Empirical Methods in Natural\n                  Language Processing, {EMNLP} 2020, Online, November 16-20, 2020},\n  pages        = {725--736},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2020},\n  url          = {https://doi.org/10.18653/v1/2020.emnlp-main.54},\n  doi          = {10.18653/V1/2020.EMNLP-MAIN.54},\n  timestamp    = {Wed, 23 Mar 2022 10:11:55 +0100},\n  biburl       = {https://dblp.org/rec/conf/emnlp/JiKHWZH20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Gated Few-shot Learning Model For Anomaly Detection.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; An, W.; He, R.; Zhao, Y.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n In 2020 International Conference on Information Networking, ICOIN 2020, Barcelona, Spain, January 7-10, 2020, pages 505–509, 2020. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/icoin/HuangLFAHZYL20,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Wanhe An and\n                  Rong He and\n                  Yining Zhao and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  title        = {A Gated Few-shot Learning Model For Anomaly Detection},\n  booktitle    = {2020 International Conference on Information Networking, {ICOIN} 2020,\n                  Barcelona, Spain, January 7-10, 2020},\n  pages        = {505--509},\n  publisher    = {{IEEE}},\n  year         = {2020},\n  url          = {https://doi.org/10.1109/ICOIN48656.2020.9016599},\n  doi          = {10.1109/ICOIN48656.2020.9016599},\n  timestamp    = {Thu, 13 Jan 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/icoin/HuangLFAHZYL20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths.\n \n \n \n \n\n\n \n Ji, H.; Ke, P.; Huang, S.; Wei, F.; and Huang, M.\n\n\n \n\n\n\n In Wong, K.; Knight, K.; and Wu, H., editor(s), Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, AACL/IJCNLP 2020, Suzhou, China, December 4-7, 2020, pages 248–257, 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"GeneratingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/ijcnlp/JiKHWH20,\n  author       = {Haozhe Ji and\n                  Pei Ke and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Minlie Huang},\n  editor       = {Kam{-}Fai Wong and\n                  Kevin Knight and\n                  Hua Wu},\n  title        = {Generating Commonsense Explanation by Extracting Bridge Concepts from\n                  Reasoning Paths},\n  booktitle    = {Proceedings of the 1st Conference of the Asia-Pacific Chapter of the\n                  Association for Computational Linguistics and the 10th International\n                  Joint Conference on Natural Language Processing, {AACL/IJCNLP} 2020,\n                  Suzhou, China, December 4-7, 2020},\n  pages        = {248--257},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2020},\n  url          = {https://aclanthology.org/2020.aacl-main.28/},\n  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/ijcnlp/JiKHWH20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LayoutLM: Pre-training of Text and Layout for Document Image Understanding.\n \n \n \n \n\n\n \n Xu, Y.; Li, M.; Cui, L.; Huang, S.; Wei, F.; and Zhou, M.\n\n\n \n\n\n\n In Gupta, R.; Liu, Y.; Tang, J.; and Prakash, B. A., editor(s), KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020, pages 1192–1200, 2020. ACM\n \n\n\n\n
\n\n\n\n \n \n \"LayoutLM:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/kdd/XuL0HW020,\n  author       = {Yiheng Xu and\n                  Minghao Li and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Ming Zhou},\n  editor       = {Rajesh Gupta and\n                  Yan Liu and\n                  Jiliang Tang and\n                  B. Aditya Prakash},\n  title        = {LayoutLM: Pre-training of Text and Layout for Document Image Understanding},\n  booktitle    = {{KDD} '20: The 26th {ACM} {SIGKDD} Conference on Knowledge Discovery\n                  and Data Mining, Virtual Event, CA, USA, August 23-27, 2020},\n  pages        = {1192--1200},\n  publisher    = {{ACM}},\n  year         = {2020},\n  url          = {https://doi.org/10.1145/3394486.3403172},\n  doi          = {10.1145/3394486.3403172},\n  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/kdd/XuL0HW020.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n TableBank: Table Benchmark for Image-based Table Detection and Recognition.\n \n \n \n \n\n\n \n Li, M.; Cui, L.; Huang, S.; Wei, F.; Zhou, M.; and Li, Z.\n\n\n \n\n\n\n In Calzolari, N.; Béchet, F.; Blache, P.; Choukri, K.; Cieri, C.; Declerck, T.; Goggi, S.; Isahara, H.; Maegaard, B.; Mariani, J.; Mazo, H.; Moreno, A.; Odijk, J.; and Piperidis, S., editor(s), Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020, pages 1918–1925, 2020. European Language Resources Association\n \n\n\n\n
\n\n\n\n \n \n \"TableBank:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/lrec/LiCHWZL20,\n  author       = {Minghao Li and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Ming Zhou and\n                  Zhoujun Li},\n  editor       = {Nicoletta Calzolari and\n                  Fr{\\'{e}}d{\\'{e}}ric B{\\'{e}}chet and\n                  Philippe Blache and\n                  Khalid Choukri and\n                  Christopher Cieri and\n                  Thierry Declerck and\n                  Sara Goggi and\n                  Hitoshi Isahara and\n                  Bente Maegaard and\n                  Joseph Mariani and\n                  H{\\'{e}}l{\\`{e}}ne Mazo and\n                  Asunci{\\'{o}}n Moreno and\n                  Jan Odijk and\n                  Stelios Piperidis},\n  title        = {TableBank: Table Benchmark for Image-based Table Detection and Recognition},\n  booktitle    = {Proceedings of The 12th Language Resources and Evaluation Conference,\n                  {LREC} 2020, Marseille, France, May 11-16, 2020},\n  pages        = {1918--1925},\n  publisher    = {European Language Resources Association},\n  year         = {2020},\n  url          = {https://aclanthology.org/2020.lrec-1.236/},\n  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/lrec/LiCHWZL20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Paddy: An Event Log Parsing Approach using Dynamic Dictionary.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Fung, C. J.; He, R.; Zhao, Y.; Yang, H.; and Luan, Z.\n\n\n \n\n\n\n In NOMS 2020 - IEEE/IFIP Network Operations and Management Symposium, Budapest, Hungary, April 20-24, 2020, pages 1–8, 2020. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"Paddy:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/noms/HuangLFHZYL20,\n  author       = {Shaohan Huang and\n                  Yi Liu and\n                  Carol J. Fung and\n                  Rong He and\n                  Yining Zhao and\n                  Hailong Yang and\n                  Zhongzhi Luan},\n  title        = {Paddy: An Event Log Parsing Approach using Dynamic Dictionary},\n  booktitle    = {{NOMS} 2020 - {IEEE/IFIP} Network Operations and Management Symposium,\n                  Budapest, Hungary, April 20-24, 2020},\n  pages        = {1--8},\n  publisher    = {{IEEE}},\n  year         = {2020},\n  url          = {https://doi.org/10.1109/NOMS47738.2020.9110435},\n  doi          = {10.1109/NOMS47738.2020.9110435},\n  timestamp    = {Wed, 15 Jun 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/noms/HuangLFHZYL20.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DocBank: A Benchmark Dataset for Document Layout Analysis.\n \n \n \n \n\n\n \n Li, M.; Xu, Y.; Cui, L.; Huang, S.; Wei, F.; Li, Z.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/2006.01038. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"DocBank:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2006-01038,\n  author       = {Minghao Li and\n                  Yiheng Xu and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Zhoujun Li and\n                  Ming Zhou},\n  title        = {DocBank: {A} Benchmark Dataset for Document Layout Analysis},\n  journal      = {CoRR},\n  volume       = {abs/2006.01038},\n  year         = {2020},\n  url          = {https://arxiv.org/abs/2006.01038},\n  eprinttype    = {arXiv},\n  eprint       = {2006.01038},\n  timestamp    = {Thu, 16 Mar 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2006-01038.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph.\n \n \n \n \n\n\n \n Ji, H.; Ke, P.; Huang, S.; Wei, F.; Zhu, X.; and Huang, M.\n\n\n \n\n\n\n CoRR, abs/2009.11692. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"LanguagePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2009-11692,\n  author       = {Haozhe Ji and\n                  Pei Ke and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Xiaoyan Zhu and\n                  Minlie Huang},\n  title        = {Language Generation with Multi-Hop Reasoning on Commonsense Knowledge\n                  Graph},\n  journal      = {CoRR},\n  volume       = {abs/2009.11692},\n  year         = {2020},\n  url          = {https://arxiv.org/abs/2009.11692},\n  eprinttype    = {arXiv},\n  eprint       = {2009.11692},\n  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2009-11692.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths.\n \n \n \n \n\n\n \n Ji, H.; Ke, P.; Huang, S.; Wei, F.; and Huang, M.\n\n\n \n\n\n\n CoRR, abs/2009.11753. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"GeneratingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2009-11753,\n  author       = {Haozhe Ji and\n                  Pei Ke and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Minlie Huang},\n  title        = {Generating Commonsense Explanation by Extracting Bridge Concepts from\n                  Reasoning Paths},\n  journal      = {CoRR},\n  volume       = {abs/2009.11753},\n  year         = {2020},\n  url          = {https://arxiv.org/abs/2009.11753},\n  eprinttype    = {arXiv},\n  eprint       = {2009.11753},\n  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2009-11753.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers.\n \n \n \n \n\n\n \n Wang, W.; Bao, H.; Huang, S.; Dong, L.; and Wei, F.\n\n\n \n\n\n\n CoRR, abs/2012.15828. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"MiniLMv2:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2012-15828,\n  author       = {Wenhui Wang and\n                  Hangbo Bao and\n                  Shaohan Huang and\n                  Li Dong and\n                  Furu Wei},\n  title        = {MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing\n                  Pretrained Transformers},\n  journal      = {CoRR},\n  volume       = {abs/2012.15828},\n  year         = {2020},\n  url          = {https://arxiv.org/abs/2012.15828},\n  eprinttype    = {arXiv},\n  eprint       = {2012.15828},\n  timestamp    = {Fri, 19 Apr 2024 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-2012-15828.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Dictionary-Guided Editing Networks for Paraphrase Generation.\n \n \n \n \n\n\n \n Huang, S.; Wu, Y.; Wei, F.; and Luan, Z.\n\n\n \n\n\n\n In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pages 6546–6553, 2019. AAAI Press\n \n\n\n\n
\n\n\n\n \n \n \"Dictionary-GuidedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/aaai/Huang0WL19,\n  author       = {Shaohan Huang and\n                  Yu Wu and\n                  Furu Wei and\n                  Zhongzhi Luan},\n  title        = {Dictionary-Guided Editing Networks for Paraphrase Generation},\n  booktitle    = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}\n                  2019, The Thirty-First Innovative Applications of Artificial Intelligence\n                  Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational\n                  Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,\n                  USA, January 27 - February 1, 2019},\n  pages        = {6546--6553},\n  publisher    = {{AAAI} Press},\n  year         = {2019},\n  url          = {https://doi.org/10.1609/aaai.v33i01.33016546},\n  doi          = {10.1609/AAAI.V33I01.33016546},\n  timestamp    = {Mon, 04 Sep 2023 12:29:24 +0200},\n  biburl       = {https://dblp.org/rec/conf/aaai/Huang0WL19.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Response Generation by Context-Aware Prototype Editing.\n \n \n \n \n\n\n \n Wu, Y.; Wei, F.; Huang, S.; Wang, Y.; Li, Z.; and Zhou, M.\n\n\n \n\n\n\n In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pages 7281–7288, 2019. AAAI Press\n \n\n\n\n
\n\n\n\n \n \n \"ResponsePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/aaai/0006WHWL019,\n  author       = {Yu Wu and\n                  Furu Wei and\n                  Shaohan Huang and\n                  Yunli Wang and\n                  Zhoujun Li and\n                  Ming Zhou},\n  title        = {Response Generation by Context-Aware Prototype Editing},\n  booktitle    = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}\n                  2019, The Thirty-First Innovative Applications of Artificial Intelligence\n                  Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational\n                  Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,\n                  USA, January 27 - February 1, 2019},\n  pages        = {7281--7288},\n  publisher    = {{AAAI} Press},\n  year         = {2019},\n  url          = {https://doi.org/10.1609/aaai.v33i01.33017281},\n  doi          = {10.1609/AAAI.V33I01.33017281},\n  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/aaai/0006WHWL019.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Neural Melody Composition from Lyrics.\n \n \n \n \n\n\n \n Bao, H.; Huang, S.; Wei, F.; Cui, L.; Wu, Y.; Tan, C.; Piao, S.; and Zhou, M.\n\n\n \n\n\n\n In Tang, J.; Kan, M.; Zhao, D.; Li, S.; and Zan, H., editor(s), Natural Language Processing and Chinese Computing - 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9-14, 2019, Proceedings, Part I, volume 11838, of Lecture Notes in Computer Science, pages 499–511, 2019. Springer\n \n\n\n\n
\n\n\n\n \n \n \"NeuralPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nlpcc/BaoHWC0TPZ19,\n  author       = {Hangbo Bao and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Lei Cui and\n                  Yu Wu and\n                  Chuanqi Tan and\n                  Songhao Piao and\n                  Ming Zhou},\n  editor       = {Jie Tang and\n                  Min{-}Yen Kan and\n                  Dongyan Zhao and\n                  Sujian Li and\n                  Hongying Zan},\n  title        = {Neural Melody Composition from Lyrics},\n  booktitle    = {Natural Language Processing and Chinese Computing - 8th {CCF} International\n                  Conference, {NLPCC} 2019, Dunhuang, China, October 9-14, 2019, Proceedings,\n                  Part {I}},\n  series       = {Lecture Notes in Computer Science},\n  volume       = {11838},\n  pages        = {499--511},\n  publisher    = {Springer},\n  year         = {2019},\n  url          = {https://doi.org/10.1007/978-3-030-32233-5\\_39},\n  doi          = {10.1007/978-3-030-32233-5\\_39},\n  timestamp    = {Wed, 26 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/nlpcc/BaoHWC0TPZ19.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n TableBank: Table Benchmark for Image-based Table Detection and Recognition.\n \n \n \n \n\n\n \n Li, M.; Cui, L.; Huang, S.; Wei, F.; Zhou, M.; and Li, Z.\n\n\n \n\n\n\n CoRR, abs/1903.01949. 2019.\n \n\n\n\n
\n\n\n\n \n \n \"TableBank:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1903-01949,\n  author       = {Minghao Li and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Ming Zhou and\n                  Zhoujun Li},\n  title        = {TableBank: Table Benchmark for Image-based Table Detection and Recognition},\n  journal      = {CoRR},\n  volume       = {abs/1903.01949},\n  year         = {2019},\n  url          = {http://arxiv.org/abs/1903.01949},\n  eprinttype    = {arXiv},\n  eprint       = {1903.01949},\n  timestamp    = {Thu, 16 Mar 2023 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1903-01949.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n LayoutLM: Pre-training of Text and Layout for Document Image Understanding.\n \n \n \n \n\n\n \n Xu, Y.; Li, M.; Cui, L.; Huang, S.; Wei, F.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/1912.13318. 2019.\n \n\n\n\n
\n\n\n\n \n \n \"LayoutLM:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1912-13318,\n  author       = {Yiheng Xu and\n                  Minghao Li and\n                  Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Ming Zhou},\n  title        = {LayoutLM: Pre-training of Text and Layout for Document Image Understanding},\n  journal      = {CoRR},\n  volume       = {abs/1912.13318},\n  year         = {2019},\n  url          = {http://arxiv.org/abs/1912.13318},\n  eprinttype    = {arXiv},\n  eprint       = {1912.13318},\n  timestamp    = {Mon, 01 Jun 2020 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1912-13318.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Neural Document Summarization by Jointly Learning to Score and Select Sentences.\n \n \n \n \n\n\n \n Zhou, Q.; Yang, N.; Wei, F.; Huang, S.; Zhou, M.; and Zhao, T.\n\n\n \n\n\n\n In Gurevych, I.; and Miyao, Y., editor(s), Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers, pages 654–663, 2018. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"NeuralPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/ZhaoZWYHZ18,\n  author       = {Qingyu Zhou and\n                  Nan Yang and\n                  Furu Wei and\n                  Shaohan Huang and\n                  Ming Zhou and\n                  Tiejun Zhao},\n  editor       = {Iryna Gurevych and\n                  Yusuke Miyao},\n  title        = {Neural Document Summarization by Jointly Learning to Score and Select\n                  Sentences},\n  booktitle    = {Proceedings of the 56th Annual Meeting of the Association for Computational\n                  Linguistics, {ACL} 2018, Melbourne, Australia, July 15-20, 2018, Volume\n                  1: Long Papers},\n  pages        = {654--663},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2018},\n  url          = {https://aclanthology.org/P18-1061/},\n  doi          = {10.18653/V1/P18-1061},\n  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/ZhaoZWYHZ18.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Response Generation by Context-aware Prototype Editing.\n \n \n \n \n\n\n \n Wu, Y.; Wei, F.; Huang, S.; Li, Z.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/1806.07042. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"ResponsePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1806-07042,\n  author       = {Yu Wu and\n                  Furu Wei and\n                  Shaohan Huang and\n                  Zhoujun Li and\n                  Ming Zhou},\n  title        = {Response Generation by Context-aware Prototype Editing},\n  journal      = {CoRR},\n  volume       = {abs/1806.07042},\n  year         = {2018},\n  url          = {http://arxiv.org/abs/1806.07042},\n  eprinttype    = {arXiv},\n  eprint       = {1806.07042},\n  timestamp    = {Wed, 26 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1806-07042.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Dictionary-Guided Editing Networks for Paraphrase Generation.\n \n \n \n \n\n\n \n Huang, S.; Wu, Y.; Wei, F.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/1806.08077. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"Dictionary-GuidedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1806-08077,\n  author       = {Shaohan Huang and\n                  Yu Wu and\n                  Furu Wei and\n                  Ming Zhou},\n  title        = {Dictionary-Guided Editing Networks for Paraphrase Generation},\n  journal      = {CoRR},\n  volume       = {abs/1806.08077},\n  year         = {2018},\n  url          = {http://arxiv.org/abs/1806.08077},\n  eprinttype    = {arXiv},\n  eprint       = {1806.08077},\n  timestamp    = {Wed, 26 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1806-08077.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Neural Document Summarization by Jointly Learning to Score and Select Sentences.\n \n \n \n \n\n\n \n Zhou, Q.; Yang, N.; Wei, F.; Huang, S.; Zhou, M.; and Zhao, T.\n\n\n \n\n\n\n CoRR, abs/1807.02305. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"NeuralPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1807-02305,\n  author       = {Qingyu Zhou and\n                  Nan Yang and\n                  Furu Wei and\n                  Shaohan Huang and\n                  Ming Zhou and\n                  Tiejun Zhao},\n  title        = {Neural Document Summarization by Jointly Learning to Score and Select\n                  Sentences},\n  journal      = {CoRR},\n  volume       = {abs/1807.02305},\n  year         = {2018},\n  url          = {http://arxiv.org/abs/1807.02305},\n  eprinttype    = {arXiv},\n  eprint       = {1807.02305},\n  timestamp    = {Wed, 25 Sep 2019 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1807-02305.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Neural Melody Composition from Lyrics.\n \n \n \n \n\n\n \n Bao, H.; Huang, S.; Wei, F.; Cui, L.; Wu, Y.; Tan, C.; Piao, S.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/1809.04318. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"NeuralPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1809-04318,\n  author       = {Hangbo Bao and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Lei Cui and\n                  Yu Wu and\n                  Chuanqi Tan and\n                  Songhao Piao and\n                  Ming Zhou},\n  title        = {Neural Melody Composition from Lyrics},\n  journal      = {CoRR},\n  volume       = {abs/1809.04318},\n  year         = {2018},\n  url          = {http://arxiv.org/abs/1809.04318},\n  eprinttype    = {arXiv},\n  eprint       = {1809.04318},\n  timestamp    = {Wed, 26 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1809-04318.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Text Morphing.\n \n \n \n \n\n\n \n Huang, S.; Wu, Y.; Wei, F.; and Zhou, M.\n\n\n \n\n\n\n CoRR, abs/1810.00341. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"TextPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-1810-00341,\n  author       = {Shaohan Huang and\n                  Yu Wu and\n                  Furu Wei and\n                  Ming Zhou},\n  title        = {Text Morphing},\n  journal      = {CoRR},\n  volume       = {abs/1810.00341},\n  year         = {2018},\n  url          = {http://arxiv.org/abs/1810.00341},\n  eprinttype    = {arXiv},\n  eprint       = {1810.00341},\n  timestamp    = {Wed, 26 Oct 2022 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/journals/corr/abs-1810-00341.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n SuperAgent: A Customer Service Chatbot for E-commerce Websites.\n \n \n \n \n\n\n \n Cui, L.; Huang, S.; Wei, F.; Tan, C.; Duan, C.; and Zhou, M.\n\n\n \n\n\n\n In Bansal, M.; and Ji, H., editor(s), Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, System Demonstrations, pages 97–102, 2017. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"SuperAgent:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/CuiHWTDZ17,\n  author       = {Lei Cui and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Chuanqi Tan and\n                  Chaoqun Duan and\n                  Ming Zhou},\n  editor       = {Mohit Bansal and\n                  Heng Ji},\n  title        = {SuperAgent: {A} Customer Service Chatbot for E-commerce Websites},\n  booktitle    = {Proceedings of the 55th Annual Meeting of the Association for Computational\n                  Linguistics, {ACL} 2017, Vancouver, Canada, July 30 - August 4, System\n                  Demonstrations},\n  pages        = {97--102},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2017},\n  url          = {https://doi.org/10.18653/v1/P17-4017},\n  doi          = {10.18653/V1/P17-4017},\n  timestamp    = {Fri, 06 Aug 2021 00:40:50 +0200},\n  biburl       = {https://dblp.org/rec/conf/acl/CuiHWTDZ17.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Arena: Adaptive real-time update anomaly prediction in cloud systems.\n \n \n \n \n\n\n \n Huang, S.; Fung, C. J.; Liu, C.; Zhang, S.; Wei, G.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In 13th International Conference on Network and Service Management, CNSM 2017, Tokyo, Japan, November 26-30, 2017, pages 1–9, 2017. IEEE Computer Society\n \n\n\n\n
\n\n\n\n \n \n \"Arena:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/cnsm/HuangFLZWLQ17,\n  author       = {Shaohan Huang and\n                  Carol J. Fung and\n                  Chang Liu and\n                  Shupeng Zhang and\n                  Guang Wei and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  title        = {Arena: Adaptive real-time update anomaly prediction in cloud systems},\n  booktitle    = {13th International Conference on Network and Service Management, {CNSM}\n                  2017, Tokyo, Japan, November 26-30, 2017},\n  pages        = {1--9},\n  publisher    = {{IEEE} Computer Society},\n  year         = {2017},\n  url          = {https://doi.org/10.23919/CNSM.2017.8256031},\n  doi          = {10.23919/CNSM.2017.8256031},\n  timestamp    = {Wed, 16 Oct 2019 14:14:54 +0200},\n  biburl       = {https://dblp.org/rec/conf/cnsm/HuangFLZWLQ17.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning to Generate Product Reviews from Attributes.\n \n \n \n \n\n\n \n Dong, L.; Huang, S.; Wei, F.; Lapata, M.; Zhou, M.; and Xu, K.\n\n\n \n\n\n\n In Lapata, M.; Blunsom, P.; and Koller, A., editor(s), Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers, pages 623–632, 2017. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/eacl/ZhouLWDHX17,\n  author       = {Li Dong and\n                  Shaohan Huang and\n                  Furu Wei and\n                  Mirella Lapata and\n                  Ming Zhou and\n                  Ke Xu},\n  editor       = {Mirella Lapata and\n                  Phil Blunsom and\n                  Alexander Koller},\n  title        = {Learning to Generate Product Reviews from Attributes},\n  booktitle    = {Proceedings of the 15th Conference of the European Chapter of the\n                  Association for Computational Linguistics, {EACL} 2017, Valencia,\n                  Spain, April 3-7, 2017, Volume 1: Long Papers},\n  pages        = {623--632},\n  publisher    = {Association for Computational Linguistics},\n  year         = {2017},\n  url          = {https://doi.org/10.18653/v1/e17-1059},\n  doi          = {10.18653/V1/E17-1059},\n  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},\n  biburl       = {https://dblp.org/rec/conf/eacl/ZhouLWDHX17.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n PSOM: Periodic Self-Organizing Maps for unsupervised anomaly detection in periodic time series.\n \n \n \n \n\n\n \n Zhang, S.; Fung, C. J.; Huang, S.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In 25th IEEE/ACM International Symposium on Quality of Service, IWQoS 2017, Vilanova i la Geltrú, Spain, June 14-16, 2017, pages 1–6, 2017. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"PSOM:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iwqos/ZhangFHLQ17,\n  author       = {Shupeng Zhang and\n                  Carol J. Fung and\n                  Shaohan Huang and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  title        = {{PSOM:} Periodic Self-Organizing Maps for unsupervised anomaly detection\n                  in periodic time series},\n  booktitle    = {25th {IEEE/ACM} International Symposium on Quality of Service, IWQoS\n                  2017, Vilanova i la Geltr{\\'{u}}, Spain, June 14-16, 2017},\n  pages        = {1--6},\n  publisher    = {{IEEE}},\n  year         = {2017},\n  url          = {https://doi.org/10.1109/IWQoS.2017.7969174},\n  doi          = {10.1109/IWQOS.2017.7969174},\n  timestamp    = {Wed, 16 Oct 2019 14:14:53 +0200},\n  biburl       = {https://dblp.org/rec/conf/iwqos/ZhangFHLQ17.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Using recurrent neural networks toward black-box system anomaly prediction.\n \n \n \n \n\n\n \n Huang, S.; Fung, C. J.; Wang, K.; Pei, P.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In 24th IEEE/ACM International Symposium on Quality of Service, IWQoS 2016, Beijing, China, June 20-21, 2016, pages 1–10, 2016. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"UsingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iwqos/HuangFWPLQ16,\n  author       = {Shaohan Huang and\n                  Carol J. Fung and\n                  Kui Wang and\n                  Polo Pei and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  title        = {Using recurrent neural networks toward black-box system anomaly prediction},\n  booktitle    = {24th {IEEE/ACM} International Symposium on Quality of Service, IWQoS\n                  2016, Beijing, China, June 20-21, 2016},\n  pages        = {1--10},\n  publisher    = {{IEEE}},\n  year         = {2016},\n  url          = {https://doi.org/10.1109/IWQoS.2016.7590435},\n  doi          = {10.1109/IWQOS.2016.7590435},\n  timestamp    = {Wed, 16 Oct 2019 14:14:53 +0200},\n  biburl       = {https://dblp.org/rec/conf/iwqos/HuangFWPLQ16.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2015\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Revisit network anomaly ranking in datacenter network using re-ranking.\n \n \n \n \n\n\n \n Huang, S.; Fung, C. J.; Wang, K.; Yang, Y.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In 4th IEEE International Conference on Cloud Networking, CloudNet 2015, Niagara Falls, ON, Canada, October 5-7, 2015, pages 178–183, 2015. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"RevisitPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/cloudnet/HuangoFWYLQ15,\n  author       = {Shaohan Huang and\n                  Carol J. Fung and\n                  Kui Wang and\n                  Yaqi Yang and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  title        = {Revisit network anomaly ranking in datacenter network using re-ranking},\n  booktitle    = {4th {IEEE} International Conference on Cloud Networking, CloudNet\n                  2015, Niagara Falls, ON, Canada, October 5-7, 2015},\n  pages        = {178--183},\n  publisher    = {{IEEE}},\n  year         = {2015},\n  url          = {https://doi.org/10.1109/CloudNet.2015.7335302},\n  doi          = {10.1109/CLOUDNET.2015.7335302},\n  timestamp    = {Mon, 03 Jan 2022 00:00:00 +0100},\n  biburl       = {https://dblp.org/rec/conf/cloudnet/HuangoFWYLQ15.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A methodology for root-cause analysis in component based systems.\n \n \n \n \n\n\n \n Wang, K.; Fung, C. J.; Ding, C.; Pei, P.; Huang, S.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In 23rd IEEE International Symposium on Quality of Service, IWQoS 2015, Portland, OR, USA, June 15-16, 2015, pages 243–248, 2015. IEEE\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iwqos/WangFDPHLQ15,\n  author       = {Kui Wang and\n                  Carol J. Fung and\n                  Chao Ding and\n                  Polo Pei and\n                  Shaohan Huang and\n                  Zhongzhi Luan and\n                  Depei Qian},\n  title        = {A methodology for root-cause analysis in component based systems},\n  booktitle    = {23rd {IEEE} International Symposium on Quality of Service, IWQoS 2015,\n                  Portland, OR, USA, June 15-16, 2015},\n  pages        = {243--248},\n  publisher    = {{IEEE}},\n  year         = {2015},\n  url          = {https://doi.org/10.1109/IWQoS.2015.7404741},\n  doi          = {10.1109/IWQOS.2015.7404741},\n  timestamp    = {Wed, 16 Oct 2019 14:14:53 +0200},\n  biburl       = {https://dblp.org/rec/conf/iwqos/WangFDPHLQ15.bib},\n  bibsource    = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n\n \n \n \n \n\n
\n"}; document.write(bibbase_data.data);