Neural Natural Language Inference Models Enhanced with External Knowledge

Neural Natural Language Inference Models Enhanced with External Knowledge. Chen, Q., Zhu, X., Ling, Z., Inkpen, D., & Wei, S.

Paper abstract bibtex

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.

@article{chenNeuralNaturalLanguage2017,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1711.04289},
  primaryClass = {cs},
  title = {Neural {{Natural Language Inference Models Enhanced}} with {{External Knowledge}}},
  url = {http://arxiv.org/abs/1711.04289},
  abstract = {Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.},
  urldate = {2019-04-30},
  date = {2017-11-12},
  keywords = {Computer Science - Computation and Language},
  author = {Chen, Qian and Zhu, Xiaodan and Ling, Zhen-Hua and Inkpen, Diana and Wei, Si},
  file = {/home/dimitri/Nextcloud/Zotero/storage/TM3J9VAZ/Chen et al. - 2017 - Neural Natural Language Inference Models Enhanced .pdf;/home/dimitri/Nextcloud/Zotero/storage/5KNZ9MVE/1711.html}
}

Downloads: 0

{"_id":"x7Yeo73D9WN7BWLD5","bibbaseid":"chen-zhu-ling-inkpen-wei-neuralnaturallanguageinferencemodelsenhancedwithexternalknowledge","authorIDs":[],"author_short":["Chen, Q.","Zhu, X.","Ling, Z.","Inkpen, D.","Wei, S."],"bibdata":{"bibtype":"article","type":"article","archiveprefix":"arXiv","eprinttype":"arxiv","eprint":"1711.04289","primaryclass":"cs","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","url":"http://arxiv.org/abs/1711.04289","abstract":"Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.","urldate":"2019-04-30","date":"2017-11-12","keywords":"Computer Science - Computation and Language","author":[{"propositions":[],"lastnames":["Chen"],"firstnames":["Qian"],"suffixes":[]},{"propositions":[],"lastnames":["Zhu"],"firstnames":["Xiaodan"],"suffixes":[]},{"propositions":[],"lastnames":["Ling"],"firstnames":["Zhen-Hua"],"suffixes":[]},{"propositions":[],"lastnames":["Inkpen"],"firstnames":["Diana"],"suffixes":[]},{"propositions":[],"lastnames":["Wei"],"firstnames":["Si"],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/TM3J9VAZ/Chen et al. - 2017 - Neural Natural Language Inference Models Enhanced .pdf;/home/dimitri/Nextcloud/Zotero/storage/5KNZ9MVE/1711.html","bibtex":"@article{chenNeuralNaturalLanguage2017,\n archivePrefix = {arXiv},\n eprinttype = {arxiv},\n eprint = {1711.04289},\n primaryClass = {cs},\n title = {Neural {{Natural Language Inference Models Enhanced}} with {{External Knowledge}}},\n url = {http://arxiv.org/abs/1711.04289},\n abstract = {Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.},\n urldate = {2019-04-30},\n date = {2017-11-12},\n keywords = {Computer Science - Computation and Language},\n author = {Chen, Qian and Zhu, Xiaodan and Ling, Zhen-Hua and Inkpen, Diana and Wei, Si},\n file = {/home/dimitri/Nextcloud/Zotero/storage/TM3J9VAZ/Chen et al. - 2017 - Neural Natural Language Inference Models Enhanced .pdf;/home/dimitri/Nextcloud/Zotero/storage/5KNZ9MVE/1711.html}\n}\n\n","author_short":["Chen, Q.","Zhu, X.","Ling, Z.","Inkpen, D.","Wei, S."],"key":"chenNeuralNaturalLanguage2017","id":"chenNeuralNaturalLanguage2017","bibbaseid":"chen-zhu-ling-inkpen-wei-neuralnaturallanguageinferencemodelsenhancedwithexternalknowledge","role":"author","urls":{"Paper":"http://arxiv.org/abs/1711.04289"},"keyword":["Computer Science - Computation and Language"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.345Z","downloads":0,"keywords":["computer science - computation and language"],"search_terms":["neural","natural","language","inference","models","enhanced","external","knowledge","chen","zhu","ling","inkpen","wei"],"title":"Neural Natural Language Inference Models Enhanced with External Knowledge","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}