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%3A%2F%2Fraw.githubusercontent.com%2Fnortheastern-datalab%2Ftable-discovery-tutorial-slides%2Fmain%2Fcitations.bib&commas=true&jsonp=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https%3A%2F%2Fraw.githubusercontent.com%2Fnortheastern-datalab%2Ftable-discovery-tutorial-slides%2Fmain%2Fcitations.bib&commas=true&jsonp=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https%3A%2F%2Fraw.githubusercontent.com%2Fnortheastern-datalab%2Ftable-discovery-tutorial-slides%2Fmain%2Fcitations.bib&commas=true&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
  2. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
    3. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2023\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning.\n \n \n \n\n\n \n Fan, G., Wang, J., Li, Y., Zhang, D., & Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 16(7): 1726–1739. 2023.\n \n\n\n\n
\n\n\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/pvldb/FanWLZM23,\n  author       = {Grace Fan and\n                  Jin Wang and\n                  Yuliang Li and\n                  Dan Zhang and\n                  Ren{\\'{e}}e J. Miller},\n  title        = {Semantics-aware Dataset Discovery from Data Lakes with Contextualized\n                  Column-based Representation Learning},\n  journal      = {Proc. {VLDB} Endow.},\n  volume       = {16},\n  number       = {7},\n  pages        = {1726--1739},\n  year         = {2023}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n SANTOS: Relationship-based Semantic Table Union Search.\n \n \n \n\n\n \n Khatiwada, A., Fan, G., Shraga, R., Chen, Z., Gatterbauer, W., Miller, R. J., & Riedewald, M.\n\n\n \n\n\n\n In SIGMOD, 2023. \n \n\n\n\n
\n\n\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{santos23,\n\tauthor    = {Aamod Khatiwada and\n\tGrace Fan and\n\tRoee Shraga and\n\tZixuan Chen and\n\tWolfgang Gatterbauer and\n\tRenée J. Miller and\n\tMirek Riedewald},\n\ttitle     = {SANTOS: Relationship-based Semantic Table Union Search},\n\tbooktitle = {SIGMOD},\n\tyear      = {2023}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Data Lake Organization.\n \n \n \n\n\n \n Nargesian, F., Pu, K. Q., Bashardoost, B. G., Zhu, E., & Miller, R. J.\n\n\n \n\n\n\n IEEE Trans. Knowl. Data Eng., 35(1): 237–250. 2023.\n \n\n\n\n
\n\n\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/tkde/NargesianPBZM23,\n  author    = {Fatemeh Nargesian and\n               Ken Q. Pu and\n               Bahar Ghadiri Bashardoost and\n               Erkang Zhu and\n               Ren{\\'{e}}e J. Miller},\n  title     = {Data Lake Organization},\n  journal   = {{IEEE} Trans. Knowl. Data Eng.},\n  volume    = {35},\n  number    = {1},\n  pages     = {237--250},\n  year      = {2023}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Annotating Columns with Pre-trained Language Models.\n \n \n \n\n\n \n Suhara, Y., Li, J., Li, Y., Zhang, D., Demiralp, Ç., Chen, C., & Tan, W.\n\n\n \n\n\n\n In SIGMOD, pages 1493–1503, 2022. \n \n\n\n\n
\n\n\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/sigmod/SuharaL0ZDCT22,\n\tauthor    = {Yoshihiko Suhara and\n\t\tJinfeng Li and\n\t\tYuliang Li and\n\t\tDan Zhang and\n\t\t{\\c{C}}agatay Demiralp and\n\t\tChen Chen and\n\t\tWang{-}Chiew Tan},\n\ttitle     = {Annotating Columns with Pre-trained Language Models},\n\tbooktitle = {SIGMOD},\n\tpages     = {1493--1503},\n\tyear      = {2022}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation.\n \n \n \n\n\n \n Zhao, Z., & Fernandez, R. C.\n\n\n \n\n\n\n In SIGMOD, pages 1504–1517, 2022. \n \n\n\n\n
\n\n\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/sigmod/ZhaoF22,\n\tauthor    = {Zixuan Zhao and\n\tRaul Castro Fernandez},\n\ttitle     = {Leva: Boosting Machine Learning Performance with Relational Embedding\n\tData Augmentation},\n\tbooktitle = {SIGMOD},\n\tpages     = {1504--1517},\n\tyear      = {2022}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n MATE: Multi-Attribute Table Extraction.\n \n \n \n\n\n \n Esmailoghli, M., Quiané-Ruiz, J., & Abedjan, Z.\n\n\n \n\n\n\n Proc. VLDB Endow., 15(8): 1684–1696. 2022.\n \n\n\n\n
\n\n\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/pvldb/EsmailoghliQA22,\n\tauthor    = {Mahdi Esmailoghli and\n\tJorge{-}Arnulfo Quian{\\'{e}}{-}Ruiz and\n\tZiawasch Abedjan},\n\ttitle     = {{MATE:} Multi-Attribute Table Extraction},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {15},\n\tnumber    = {8},\n\tpages     = {1684--1696},\n\tyear      = {2022}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n A Sketch-based Index for Correlated Dataset Search.\n \n \n \n\n\n \n Santos, A. S. R., Bessa, A., Musco, C., & Freire, J.\n\n\n \n\n\n\n In ICDE, pages 2928–2941, 2022. \n \n\n\n\n
\n\n\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/icde/SantosBMF22,\n\tauthor    = {A{\\'{e}}cio S. R. Santos and\n\tAline Bessa and\n\tChristopher Musco and\n\tJuliana Freire},\n\ttitle     = {A Sketch-based Index for Correlated Dataset Search},\n\tbooktitle = {ICDE},\n\tpages     = {2928--2941},\n\tyear      = {2022}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Integrating Data Lake Tables.\n \n \n \n\n\n \n Khatiwada, A., Shraga, R., Gatterbauer, W., & Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 16(4): 932–945. 2022.\n \n\n\n\n
\n\n\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/pvldb/KhatiwadaSGM22,\n  author    = {Aamod Khatiwada and\n               Roee Shraga and\n               Wolfgang Gatterbauer and\n               Ren{\\'{e}}e J. Miller},\n  title     = {Integrating Data Lake Tables},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {16},\n  number    = {4},\n  pages     = {932--945},\n  year      = {2022}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses.\n \n \n \n\n\n \n Cong, T., Gale, J., Frantz, J., Jagadish, H. V., & Demiralp, Ç.\n\n\n \n\n\n\n CoRR, abs/2212.14155. 2022.\n \n\n\n\n
\n\n\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-2212-14155,\n  author    = {Tianji Cong and\n               James Gale and\n               Jason Frantz and\n               H. V. Jagadish and\n               {\\c{C}}agatay Demiralp},\n  title     = {WarpGate: {A} Semantic Join Discovery System for Cloud Data Warehouses},\n  journal   = {CoRR},\n  volume    = {abs/2212.14155},\n  year      = {2022}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (9)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Auctus: A Dataset Search Engine for Data Discovery and Augmentation.\n \n \n \n\n\n \n Castelo, S., Rampin, R., Santos, A. S. R., Bessa, A., Chirigati, F., & Freire, J.\n\n\n \n\n\n\n Proc. VLDB Endow., 14(12): 2791–2794. 2021.\n \n\n\n\n
\n\n\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/pvldb/CasteloRSBCF21,\n\tauthor    = {Sonia Castelo and\n\tR{\\'{e}}mi Rampin and\n\tA{\\'{e}}cio S. R. Santos and\n\tAline Bessa and\n\tFernando Chirigati and\n\tJuliana Freire},\n\ttitle     = {Auctus: {A} Dataset Search Engine for Data Discovery and Augmentation},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {14},\n\tnumber    = {12},\n\tpages     = {2791--2794},\n\tyear      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n RONIN: Data Lake Exploration.\n \n \n \n\n\n \n Ouellette, P., Sciortino, A., Nargesian, F., Bashardoost, B. G., Zhu, E., Pu, K., & Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 14(12): 2863–2866. 2021.\n \n\n\n\n
\n\n\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/pvldb/OuelletteSNBZPM21,\n  author    = {Paul Ouellette and\n               Aidan Sciortino and\n               Fatemeh Nargesian and\n               Bahar Ghadiri Bashardoost and\n               Erkang Zhu and\n               Ken Pu and\n               Ren{\\'{e}}e J. Miller},\n  title     = {{RONIN:} Data Lake Exploration},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {14},\n  number    = {12},\n  pages     = {2863--2866},\n  year      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach.\n \n \n \n\n\n \n Dong, Y., Takeoka, K., Xiao, C., & Oyamada, M.\n\n\n \n\n\n\n In ICDE, pages 456–467, 2021. \n \n\n\n\n
\n\n\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/icde/DongT0O21,\n\tauthor    = {Yuyang Dong and\n\tKunihiro Takeoka and\n\tChuan Xiao and\n\tMasafumi Oyamada},\n\ttitle     = {Efficient Joinable Table Discovery in Data Lakes: {A} High-Dimensional\n\tSimilarity-Based Approach},\n\tbooktitle =  {ICDE},\n\tpages     = {456--467},\n\tyear      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Relational Header Discovery using Similarity Search in a Table Corpus.\n \n \n \n\n\n \n Harmouch, H., Papenbrock, T., & Naumann, F.\n\n\n \n\n\n\n In ICDE, pages 444–455, 2021. \n \n\n\n\n
\n\n\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/icde/HarmouchPN21,\n\tauthor    = {Hazar Harmouch and\n\tThorsten Papenbrock and\n\tFelix Naumann},\n\ttitle     = {Relational Header Discovery using Similarity Search in a Table Corpus},\n\tbooktitle = {ICDE},\n\tpages     = {444--455},\n\tyear      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Valentine: Evaluating Matching Techniques for Dataset Discovery.\n \n \n \n\n\n \n Koutras, C., Siachamis, G., Ionescu, A., Psarakis, K., Brons, J., Fragkoulis, M., Lofi, C., Bonifati, A., & Katsifodimos, A.\n\n\n \n\n\n\n In ICDE, pages 468–479, 2021. \n \n\n\n\n
\n\n\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/icde/KoutrasSIPBFLBK21,\n\tauthor    = {Christos Koutras and\n\tGeorge Siachamis and\n\tAndra Ionescu and\n\tKyriakos Psarakis and\n\tJerry Brons and\n\tMarios Fragkoulis and\n\tChristoph Lofi and\n\tAngela Bonifati and\n\tAsterios Katsifodimos},\n\ttitle     = {Valentine: Evaluating Matching Techniques for Dataset Discovery},\n\tbooktitle = {ICDE},\n\tpages     = {468--479},\n\tyear      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n TCN: Table Convolutional Network for Web Table Interpretation.\n \n \n \n\n\n \n Wang, D., Shiralkar, P., Lockard, C., Huang, B., Dong, X. L., & Jiang, M.\n\n\n \n\n\n\n In WWW, pages 4020–4032, 2021. \n \n\n\n\n
\n\n\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/www/WangSLHDJ21,\n  author    = {Daheng Wang and\n               Prashant Shiralkar and\n               Colin Lockard and\n               Binxuan Huang and\n               Xin Luna Dong and\n               Meng Jiang},\n  title     = {{TCN:} Table Convolutional Network for Web Table Interpretation},\n  booktitle = {WWW},\n  pages     = {4020--4032},\n  year      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Knowledge Graphs 2021: A Data Odyssey.\n \n \n \n\n\n \n Weikum, G.\n\n\n \n\n\n\n Proc. VLDB Endow., 14(12): 3233–3238. 2021.\n \n\n\n\n
\n\n\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/pvldb/Weikum21,\n  author    = {Gerhard Weikum},\n  title     = {Knowledge Graphs 2021: {A} Data Odyssey},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {14},\n  number    = {12},\n  pages     = {3233--3238},\n  year      = {2021}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n PLEX: Towards Practical Learned Indexing.\n \n \n \n\n\n \n Stoian, M., Kipf, A., Marcus, R., & Kraska, T.\n\n\n \n\n\n\n CoRR, abs/2108.05117. 2021.\n \n\n\n\n
\n\n\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-2108-05117,\n  author    = {Mihail Stoian and\n               Andreas Kipf and\n               Ryan Marcus and\n               Tim Kraska},\n  title     = {{PLEX:} Towards Practical Learned Indexing},\n  journal   = {CoRR},\n  volume    = {abs/2108.05117},\n  year      = {2021}\n   }\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n DomainNet: Homograph Detection for Data Lake Disambiguation.\n \n \n \n\n\n \n Leventidis, A., Rocco, L. D., Gatterbauer, W., Miller, R. J., & Riedewald, M.\n\n\n \n\n\n\n In EDBT, pages 13–24, 2021. \n \n\n\n\n
\n\n\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/edbt/LeventidisRMRG21,\n  author    = {Aristotelis Leventidis and\n               Laura Di Rocco and\n               Wolfgang Gatterbauer and\n               Ren{\\'{e}}e J. Miller and\n               Mirek Riedewald},\n  title     = {DomainNet: Homograph Detection for Data Lake Disambiguation},\n  booktitle = {EDBT},\n  pages     = {13--24},\n  year      = {2021}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (11)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Semantic Search over Structured Data.\n \n \n \n\n\n \n Galhotra, S., & Khurana, U.\n\n\n \n\n\n\n In CIKM, 2020. \n \n\n\n\n
\n\n\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/cikm/GalhotraK20,\n  author    = {Sainyam Galhotra and\n               Udayan Khurana},\n  title     = {Semantic Search over Structured Data},\n  booktitle = {CIKM},\n  year      = {2020}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Dataset search: a survey.\n \n \n \n\n\n \n Chapman, A., Simperl, E., Koesten, L., Konstantinidis, G., Ibáñez, L., Kacprzak, E., & Groth, P.\n\n\n \n\n\n\n VLDB J., 29(1): 251–272. 2020.\n \n\n\n\n
\n\n\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/vldb/ChapmanSKKIKG20,\n  author    = {Adriane Chapman and\n               Elena Simperl and\n               Laura Koesten and\n               George Konstantinidis and\n               Luis{-}Daniel Ib{\\'{a}}{\\~{n}}ez and\n               Emilia Kacprzak and\n               Paul Groth},\n  title     = {Dataset search: a survey},\n  journal   = {{VLDB} J.},\n  volume    = {29},\n  number    = {1},\n  pages     = {251--272},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n ARDA: Automatic Relational Data Augmentation for Machine Learning.\n \n \n \n\n\n \n Chepurko, N., Marcus, R., Zgraggen, E., Fernandez, R. C., Kraska, T., & Karger, D. R.\n\n\n \n\n\n\n Proc. VLDB Endow., 13(9): 1373–1387. 2020.\n \n\n\n\n
\n\n\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/pvldb/ChepurkoMZFKK20,\n  author    = {Nadiia Chepurko and\n               Ryan Marcus and\n               Emanuel Zgraggen and\n               Raul Castro Fernandez and\n               Tim Kraska and\n               David R. Karger},\n  title     = {{ARDA:} Automatic Relational Data Augmentation for Machine Learning},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {13},\n  number    = {9},\n  pages     = {1373--1387},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Sato: Contextual Semantic Type Detection in Tables.\n \n \n \n\n\n \n Zhang, D., Suhara, Y., Li, J., Hulsebos, M., Demiralp, Ç., & Tan, W.\n\n\n \n\n\n\n Proc. VLDB Endow., 13(11): 1835–1848. 2020.\n \n\n\n\n
\n\n\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/pvldb/ZhangSLHDT20,\n  author    = {Dan Zhang and\n               Yoshihiko Suhara and\n               Jinfeng Li and\n               Madelon Hulsebos and\n               {\\c{C}}agatay Demiralp and\n               Wang{-}Chiew Tan},\n  title     = {Sato: Contextual Semantic Type Detection in Tables},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {13},\n  number    = {11},\n  pages     = {1835--1848},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Data-Driven Domain Discovery for Structured Datasets.\n \n \n \n\n\n \n Ota, M., Mueller, H., Freire, J., & Srivastava, D.\n\n\n \n\n\n\n Proc. VLDB Endow., 13(7): 953–965. 2020.\n \n\n\n\n
\n\n\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/pvldb/OtaMFS20,\n\tauthor    = {Masayo Ota and\n\tHeiko Mueller and\n\tJuliana Freire and\n\tDivesh Srivastava},\n\ttitle     = {Data-Driven Domain Discovery for Structured Datasets},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {13},\n\tnumber    = {7},\n\tpages     = {953--965},\n\tyear      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n TURL: Table Understanding through Representation Learning.\n \n \n \n\n\n \n Deng, X., Sun, H., Lees, A., Wu, Y., & Yu, C.\n\n\n \n\n\n\n Proc. VLDB Endow., 14(3): 307–319. 2020.\n \n\n\n\n
\n\n\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/pvldb/DengSL0020,\n\tauthor    = {Xiang Deng and\n\tHuan Sun and\n\tAlyssa Lees and\n\tYou Wu and\n\tCong Yu},\n\ttitle     = {{TURL:} Table Understanding through Representation Learning},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {14},\n\tnumber    = {3},\n\tpages     = {307--319},\n\tyear      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Organizing Data Lakes for Navigation.\n \n \n \n\n\n \n Nargesian, F., Pu, K. Q., Zhu, E., Bashardoost, B. G., & Miller, R. J.\n\n\n \n\n\n\n In SIGMOD, pages 1939–1950, 2020. \n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 9 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{DBLP:conf/sigmod/NargesianPZBM20,\n  author    = {Fatemeh Nargesian and\n               Ken Q. Pu and\n               Erkang Zhu and\n               Bahar Ghadiri Bashardoost and\n               Ren{\\'{e}}e J. Miller},\n  title     = {Organizing Data Lakes for Navigation},\n  booktitle = {SIGMOD},\n  pages     = {1939--1950},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Finding Related Tables in Data Lakes for Interactive Data Science.\n \n \n \n\n\n \n Zhang, Y., & Ives, Z. G.\n\n\n \n\n\n\n In SIGMOD, pages 1951–1966, 2020. \n \n\n\n\n
\n\n\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/sigmod/ZhangI20,\n\tauthor    = {Yi Zhang and\n\tZachary G. Ives},\n\ttitle     = {Finding Related Tables in Data Lakes for Interactive Data Science},\n\tbooktitle = {SIGMOD},\n\tpages     = {1951--1966},\n\tyear      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks.\n \n \n \n\n\n \n Cappuzzo, R., Papotti, P., & Thirumuruganathan, S.\n\n\n \n\n\n\n In SIGMOD, pages 1335–1349, 2020. \n \n\n\n\n
\n\n\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/sigmod/CappuzzoPT20,\n  author    = {Riccardo Cappuzzo and\n               Paolo Papotti and\n               Saravanan Thirumuruganathan},\n  title     = {Creating Embeddings of Heterogeneous Relational Datasets for Data\n               Integration Tasks},\n  booktitle = {SIGMOD},\n  pages     = {1335--1349},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Dataset Discovery in Data Lakes.\n \n \n \n\n\n \n Bogatu, A., Fernandes, A. A. A., Paton, N. W., & Konstantinou, N.\n\n\n \n\n\n\n In ICDE, pages 709–720, 2020. \n \n\n\n\n
\n\n\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/icde/BogatuFP020,\n\tauthor    = {Alex Bogatu and\n\tAlvaro A. A. Fernandes and\n\tNorman W. Paton and\n\tNikolaos Konstantinou},\n\ttitle     = {Dataset Discovery in Data Lakes},\n\tbooktitle = {ICDE},\n\tpages     = {709--720},\n\tyear      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs.\n \n \n \n\n\n \n Malkov, Y. A., & Yashunin, D. A.\n\n\n \n\n\n\n IEEE Trans. Pattern Anal. Mach. Intell., 42(4): 824–836. 2020.\n \n\n\n\n
\n\n\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/pami/MalkovY20,\n  author    = {Yury A. Malkov and\n               Dmitry A. Yashunin},\n  title     = {Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical\n               Navigable Small World Graphs},\n  journal   = {{IEEE} Trans. Pattern Anal. Mach. Intell.},\n  volume    = {42},\n  number    = {4},\n  pages     = {824--836},\n  year      = {2020}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Sherlock: A Deep Learning Approach to Semantic Data Type Detection.\n \n \n \n\n\n \n Hulsebos, M., Hu, K. Z., Bakker, M. A., Zgraggen, E., Satyanarayan, A., Kraska, T., Demiralp, Ç., & Hidalgo, C. A.\n\n\n \n\n\n\n In SIGKDD, pages 1500–1508, 2019. \n \n\n\n\n
\n\n\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/kdd/HulsebosHBZSKDH19,\n  author    = {Madelon Hulsebos and\n               Kevin Zeng Hu and\n               Michiel A. Bakker and\n               Emanuel Zgraggen and\n               Arvind Satyanarayan and\n               Tim Kraska and\n               {\\c{C}}agatay Demiralp and\n               C{\\'{e}}sar A. Hidalgo},\n  title     = {Sherlock: {A} Deep Learning Approach to Semantic Data Type Detection},\n  booktitle = {SIGKDD},\n  pages     = {1500--1508},\n  year      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Google Dataset Search: Building a search engine for datasets in an open Web ecosystem.\n \n \n \n\n\n \n Brickley, D., Burgess, M., & Noy, N. F.\n\n\n \n\n\n\n In WWW, pages 1365–1375, 2019. \n \n\n\n\n
\n\n\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/www/BrickleyBN19,\n\tauthor    = {Dan Brickley and\n\tMatthew Burgess and\n\tNatasha F. Noy},\n\ttitle     = {Google Dataset Search: Building a search engine for datasets in an\n\topen Web ecosystem},\n\tbooktitle =  {WWW},\n\tpages     = {1365--1375},\n\tyear      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems.\n \n \n \n\n\n \n Idreos, S., & Kraska, T.\n\n\n \n\n\n\n In SIGMOD, pages 2054–2059, 2019. \n \n\n\n\n
\n\n\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/sigmod/IdreosK19,\n  author    = {Stratos Idreos and\n               Tim Kraska},\n  title     = {From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive\n               Systems},\n  booktitle = {SIGMOD},\n  pages     = {2054--2059},\n  year      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n JOSIE: Overlap Set Similarity Search for Finding Joinable Tables in Data Lakes.\n \n \n \n\n\n \n Zhu, E., Deng, D., Nargesian, F., & Miller, R. J.\n\n\n \n\n\n\n In SIGMOD, pages 847–864, 2019. \n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{DBLP:conf/sigmod/ZhuDNM19,\n\tauthor    = {Erkang Zhu and\n\tDong Deng and\n\tFatemeh Nargesian and\n\tRen{\\'{e}}e J. Miller},\n\ttitle     = {{JOSIE:} Overlap Set Similarity Search for Finding Joinable Tables\n\tin Data Lakes},\n\tbooktitle = {SIGMOD},\n\tpages     = {847--864},\n\tyear      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Data Lake Management: Challenges and Opportunities.\n \n \n \n\n\n \n Nargesian, F., Zhu, E., Miller, R. J., Pu, K. Q., & Arocena, P. C.\n\n\n \n\n\n\n Proc. VLDB Endow., 12(12): 1986–1989. 2019.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{DBLP:journals/pvldb/NargesianZMPA19,\n\tauthor    = {Fatemeh Nargesian and\n\tErkang Zhu and\n\tRen{\\'{e}}e J. Miller and\n\tKen Q. Pu and\n\tPatricia C. Arocena},\n\ttitle     = {Data Lake Management: Challenges and Opportunities},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {12},\n\tnumber    = {12},\n\tpages     = {1986--1989},\n\tyear      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Synergy of Database Techniques and Machine Learning Models for String Similarity Search and Join.\n \n \n \n\n\n \n Lu, J., Lin, C., Wang, J., & Li, C.\n\n\n \n\n\n\n In CIKM, pages 2975–2976, 2019. \n \n\n\n\n
\n\n\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/cikm/LuLW019,\n  author    = {Jiaheng Lu and\n               Chunbin Lin and\n               Jin Wang and\n               Chen Li},\n  title     = {Synergy of Database Techniques and Machine Learning Models for String\n               Similarity Search and Join},\n  booktitle = {CIKM},\n  pages     = {2975--2976},\n  year      = {2019}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (8)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Making Open Data Transparent: Data Discovery on Open Data.\n \n \n \n\n\n \n Miller, R. J., Nargesian, F., Zhu, E., Christodoulakis, C., Pu, K. Q., & Andritsos, P.\n\n\n \n\n\n\n IEEE Data Eng. Bull., 41(2): 59–70. 2018.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{DBLP:journals/debu/MillerNZCPA18,\n\tauthor    = {Ren{\\'{e}}e J. Miller and\n\tFatemeh Nargesian and\n\tErkang Zhu and\n\tChristina Christodoulakis and\n\tKen Q. Pu and\n\tPeriklis Andritsos},\n\ttitle     = {Making Open Data Transparent: Data Discovery on Open Data},\n\tjournal   = {{IEEE} Data Eng. Bull.},\n\tvolume    = {41},\n\tnumber    = {2},\n\tpages     = {59--70},\n\tyear      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Table Union Search on Open Data.\n \n \n \n\n\n \n Nargesian, F., Zhu, E., Pu, K. Q., & Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 11(7): 813–825. 2018.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{DBLP:journals/pvldb/NargesianZPM18,\n\tauthor    = {Fatemeh Nargesian and\n\t\tErkang Zhu and\n\t\tKen Q. Pu and\n\t\tRen{\\'{e}}e J. Miller},\n\ttitle     = {Table Union Search on Open Data},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {11},\n\tnumber    = {7},\n\tpages     = {813--825},\n\tyear      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web.\n \n \n \n\n\n \n Lockard, C., Dong, X. L., Shiralkar, P., & Einolghozati, A.\n\n\n \n\n\n\n Proc. VLDB Endow., 11(10): 1084–1096. 2018.\n \n\n\n\n
\n\n\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/pvldb/LockardDSE18,\n  author    = {Colin Lockard and\n               Xin Luna Dong and\n               Prashant Shiralkar and\n               Arash Einolghozati},\n  title     = {{CERES:} Distantly Supervised Relation Extraction from the Semi-Structured\n               Web},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {11},\n  number    = {10},\n  pages     = {1084--1096},\n  year      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Open Data Integration.\n \n \n \n\n\n \n Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 11(12): 2130–2139. 2018.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{DBLP:journals/pvldb/Miller18,\n  author    = {Ren{\\'{e}}e J. Miller},\n  title     = {Open Data Integration},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {11},\n  number    = {12},\n  pages     = {2130--2139},\n  year      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery.\n \n \n \n\n\n \n Fernandez, R. C., Mansour, E., Qahtan, A. A., Elmagarmid, A. K., Ilyas, I. F., Madden, S., Ouzzani, M., Stonebraker, M., & Tang, N.\n\n\n \n\n\n\n In ICDE, pages 989–1000, 2018. \n \n\n\n\n
\n\n\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/icde/FernandezMQEIMO18,\n\tauthor    = {Raul Castro Fernandez and\n\tEssam Mansour and\n\tAbdulhakim Ali Qahtan and\n\tAhmed K. Elmagarmid and\n\tIhab F. Ilyas and\n\tSamuel Madden and\n\tMourad Ouzzani and\n\tMichael Stonebraker and\n\tNan Tang},\n\ttitle     = {Seeping Semantics: Linking Datasets Using Word Embeddings for Data\n\tDiscovery},\n\tbooktitle = {ICDE},\n\tpages     = {989--1000},\n\tyear      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Aurum: A Data Discovery System.\n \n \n \n\n\n \n Fernandez, R. C., Abedjan, Z., Koko, F., Yuan, G., Madden, S., & Stonebraker, M.\n\n\n \n\n\n\n In ICDE, pages 1001–1012, 2018. \n \n\n\n\n
\n\n\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/icde/FernandezAKYMS18,\n\tauthor    = {Raul Castro Fernandez and\n\tZiawasch Abedjan and\n\tFamien Koko and\n\tGina Yuan and\n\tSamuel Madden and\n\tMichael Stonebraker},\n\ttitle     = {Aurum: {A} Data Discovery System},\n\tbooktitle =  {ICDE},\n\tpages     = {1001--1012},\n\tyear      = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n The Periodic Table of Data Structures.\n \n \n \n\n\n \n Idreos, S., Zoumpatianos, K., Athanassoulis, M., Dayan, N., Hentschel, B., Kester, M. S., Guo, D., Maas, L. M., Qin, W., Wasay, A., & Sun, Y.\n\n\n \n\n\n\n IEEE Data Eng. Bull., 41(3): 64–75. 2018.\n \n\n\n\n
\n\n\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/debu/IdreosZADHKGMQW18,\n  author    = {Stratos Idreos and\n               Kostas Zoumpatianos and\n               Manos Athanassoulis and\n               Niv Dayan and\n               Brian Hentschel and\n               Michael S. Kester and\n               Demi Guo and\n               Lukas M. Maas and\n               Wilson Qin and\n               Abdul Wasay and\n               Yiyou Sun},\n  title     = {The Periodic Table of Data Structures},\n  journal   = {{IEEE} Data Eng. Bull.},\n  volume    = {41},\n  number    = {3},\n  pages     = {64--75},\n  year      = {2018}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Open Data Integration.\n \n \n \n\n\n \n Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 11(12): 2130–2139. 2018.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{DBLP:journals/pvldb/Miller18,\n  author    = {Ren{\\'{e}}e J. Miller},\n  title     = {Open Data Integration},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {11},\n  number    = {12},\n  pages     = {2130--2139},\n  year      = {2018}\n}
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Stitching Web Tables for Improving Matching Quality.\n \n \n \n\n\n \n Lehmberg, O., & Bizer, C.\n\n\n \n\n\n\n Proc. VLDB Endow., 10(11): 1502–1513. 2017.\n \n\n\n\n
\n\n\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/pvldb/LehmbergB17,\n\tauthor    = {Oliver Lehmberg and\n\tChristian Bizer},\n\ttitle     = {Stitching Web Tables for Improving Matching Quality},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {10},\n\tnumber    = {11},\n\tpages     = {1502--1513},\n\tyear      = {2017}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Discovering Enterprise Concepts Using Spreadsheet Tables.\n \n \n \n\n\n \n Li, K., He, Y., & Ganjam, K.\n\n\n \n\n\n\n In SIGKDD, pages 1873–1882, 2017. \n \n\n\n\n
\n\n\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/kdd/LiHG17,\n  author    = {Keqian Li and\n               Yeye He and\n               Kris Ganjam},\n  title     = {Discovering Enterprise Concepts Using Spreadsheet Tables},\n  booktitle = {SIGKDD},\n  pages     = {1873--1882},\n  year      = {2017}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n A Large Public Corpus of Web Tables containing Time and Context Metadata.\n \n \n \n\n\n \n Lehmberg, O., Ritze, D., Meusel, R., & Bizer, C.\n\n\n \n\n\n\n In WWW, pages 75–76, 2016. \n \n\n\n\n
\n\n\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/www/LehmbergRMB16,\n  author    = {Oliver Lehmberg and\n               Dominique Ritze and\n               Robert Meusel and\n               Christian Bizer},\n  title     = {A Large Public Corpus of Web Tables containing Time and Context Metadata},\n  booktitle = {WWW},\n  pages     = {75--76},\n  year      = {2016}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n LSH Ensemble: Internet-Scale Domain Search.\n \n \n \n\n\n \n Zhu, E., Nargesian, F., Pu, K. Q., & Miller, R. J.\n\n\n \n\n\n\n Proc. VLDB Endow., 9(12): 1185–1196. 2016.\n \n\n\n\n
\n\n\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/pvldb/ZhuNPM16,\n\tauthor    = {Erkang Zhu and\n\tFatemeh Nargesian and\n\tKen Q. Pu and\n\tRen{\\'{e}}e J. Miller},\n\ttitle     = {{LSH} Ensemble: Internet-Scale Domain Search},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {9},\n\tnumber    = {12},\n\tpages     = {1185--1196},\n\tyear      = {2016}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Goods: Organizing Google's Datasets.\n \n \n \n\n\n \n Halevy, A. Y., Korn, F., Noy, N. F., Olston, C., Polyzotis, N., Roy, S., & Whang, S. E.\n\n\n \n\n\n\n In SIGMOD, pages 795–806, 2016. \n \n\n\n\n
\n\n\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/sigmod/HalevyKNOPRW16,\n  author    = {Alon Y. Halevy and\n               Flip Korn and\n               Natalya Fridman Noy and\n               Christopher Olston and\n               Neoklis Polyzotis and\n               Sudip Roy and\n               Steven Euijong Whang},\n  title     = {Goods: Organizing Google's Datasets},\n  booktitle = {SIGMOD},\n  pages     = {795--806},\n  year      = {2016}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Extracting Databases from Dark Data with DeepDive.\n \n \n \n\n\n \n Zhang, C., Shin, J., Ré, C., Cafarella, M. J., & Niu, F.\n\n\n \n\n\n\n In SIGMOD, pages 847–859, 2016. \n \n\n\n\n
\n\n\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/sigmod/Zhang0RCN16,\n  author    = {Ce Zhang and\n               Jaeho Shin and\n               Christopher R{\\'{e}} and\n               Michael J. Cafarella and\n               Feng Niu},\n  title     = {Extracting Databases from Dark Data with DeepDive},\n  booktitle = {SIGMOD},\n  pages     = {847--859},\n  year      = {2016}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n CLAMS: Bringing Quality to Data Lakes.\n \n \n \n\n\n \n Farid, M. H., Roatis, A., Ilyas, I. F., Hoffmann, H., & Chu, X.\n\n\n \n\n\n\n In SIGMOD, pages 2089–2092, 2016. \n \n\n\n\n
\n\n\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/sigmod/FaridRIHC16,\n  author    = {Mina H. Farid and\n               Alexandra Roatis and\n               Ihab F. Ilyas and\n               Hella{-}Franziska Hoffmann and\n               Xu Chu},\n  title     = {{CLAMS:} Bringing Quality to Data Lakes},\n  booktitle = {SIGMOD},\n  pages     = {2089--2092},\n  year      = {2016}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2015\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n The Mannheim Search Join Engine.\n \n \n \n\n\n \n Lehmberg, O., Ritze, D., Ristoski, P., Meusel, R., Paulheim, H., & Bizer, C.\n\n\n \n\n\n\n J. Web Semant., 35: 159–166. 2015.\n \n\n\n\n
\n\n\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/ws/LehmbergRRMPB15,\n  author    = {Oliver Lehmberg and\n               Dominique Ritze and\n               Petar Ristoski and\n               Robert Meusel and\n               Heiko Paulheim and\n               Christian Bizer},\n  title     = {The Mannheim Search Join Engine},\n  journal   = {J. Web Semant.},\n  volume    = {35},\n  pages     = {159--166},\n  year      = {2015}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n How government can promote open data.\n \n \n \n\n\n \n Chui, M., Farrell, D., & Jackson, K.\n\n\n \n\n\n\n McKinsey Company. 2014.\n \n\n\n\n
\n\n\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{chui2014government,\n  title={How government can promote open data},\n  author={Chui, Michael and Farrell, Diana and Jackson, Kate},\n  journal={McKinsey Company},\n  year={2014}\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n MeanKS: meaningful keyword search in relational databases with complex schema.\n \n \n \n\n\n \n Kargar, M., An, A., Cercone, N., Godfrey, P., Szlichta, J., & Yu, X.\n\n\n \n\n\n\n In SIGMOD, pages 905–908, 2014. \n \n\n\n\n
\n\n\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/sigmod/KargarACGSY14,\n  author    = {Mehdi Kargar and\n               Aijun An and\n               Nick Cercone and\n               Parke Godfrey and\n               Jaroslaw Szlichta and\n               Xiaohui Yu},\n  title     = {MeanKS: meaningful keyword search in relational databases with complex\n               schema},\n  booktitle = {SIGMOD},\n  pages     = {905--908},\n  year      = {2014}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n An Empirical Performance Evaluation of Relational Keyword Search Techniques.\n \n \n \n\n\n \n Coffman, J., & Weaver, A. C.\n\n\n \n\n\n\n IEEE Trans. Knowl. Data Eng., 26(1): 30–42. 2014.\n \n\n\n\n
\n\n\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/tkde/CoffmanW14,\n  author    = {Joel Coffman and\n               Alfred C. Weaver},\n  title     = {An Empirical Performance Evaluation of Relational Keyword Search Techniques},\n  journal   = {{IEEE} Trans. Knowl. Data Eng.},\n  volume    = {26},\n  number    = {1},\n  pages     = {30--42},\n  year      = {2014}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2013\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Synthesizing Union Tables from the Web.\n \n \n \n\n\n \n Ling, X., Halevy, A. Y., Wu, F., & Yu, C.\n\n\n \n\n\n\n In IJCAI, pages 2677–2683, 2013. \n \n\n\n\n
\n\n\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/ijcai/LingH0Y13,\n  author    = {Xiao Ling and\n               Alon Y. Halevy and\n               Fei Wu and\n               Cong Yu},\n  title     = {Synthesizing Union Tables from the Web},\n  booktitle = {IJCAI},\n  pages     = {2677--2683},\n  year      = {2013}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Schema Extraction for Tabular Data on the Web.\n \n \n \n\n\n \n Adelfio, M. D., & Samet, H.\n\n\n \n\n\n\n Proc. VLDB Endow., 6(6): 421–432. 2013.\n \n\n\n\n
\n\n\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/pvldb/AdelfioS13,\n  author    = {Marco D. Adelfio and\n               Hanan Samet},\n  title     = {Schema Extraction for Tabular Data on the Web},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {6},\n  number    = {6},\n  pages     = {421--432},\n  year      = {2013}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2012\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n InfoGather: entity augmentation and attribute discovery by holistic matching with web tables.\n \n \n \n\n\n \n Yakout, M., Ganjam, K., Chakrabarti, K., & Chaudhuri, S.\n\n\n \n\n\n\n In SIGMOD, pages 97–108, 2012. \n \n\n\n\n
\n\n\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/sigmod/YakoutGCC12,\n\tauthor    = {Mohamed Yakout and\n\tKris Ganjam and\n\tKaushik Chakrabarti and\n\tSurajit Chaudhuri},\n\ttitle     = {InfoGather: entity augmentation and attribute discovery by holistic\n\tmatching with web tables},\n\tbooktitle = {SIGMOD} ,\n\tpages     = {97--108},\n\tyear      = {2012}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Answering Table Queries on the Web using Column Keywords.\n \n \n \n\n\n \n Pimplikar, R., & Sarawagi, S.\n\n\n \n\n\n\n Proc. VLDB Endow., 5(10): 908–919. 2012.\n \n\n\n\n
\n\n\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/pvldb/PimplikarS12,\n  author    = {Rakesh Pimplikar and\n               Sunita Sarawagi},\n  title     = {Answering Table Queries on the Web using Column Keywords},\n  journal   = {Proc. {VLDB} Endow.},\n  volume    = {5},\n  number    = {10},\n  pages     = {908--919},\n  year      = {2012}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Finding related tables.\n \n \n \n\n\n \n Das Sarma, A., Fang, L., Gupta, N., Halevy, A. Y., Lee, H., Wu, F., Xin, R., & Yu, C.\n\n\n \n\n\n\n In SIGMOD, pages 817–828, 2012. \n \n\n\n\n
\n\n\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/sigmod/SarmaFGHLWXY12,\n\tauthor    = {Anish {Das Sarma} and\n\tLujun Fang and\n\tNitin Gupta and\n\tAlon Y. Halevy and\n\tHongrae Lee and\n\tFei Wu and\n\tReynold Xin and\n\tCong Yu},\n\ttitle     = {Finding related tables},\n\tbooktitle = {SIGMOD},\n\tpages     = {817--828},\n\tyear      = {2012}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2011\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Recovering Semantics of Tables on the Web.\n \n \n \n\n\n \n Venetis, P., Halevy, A. Y., Madhavan, J., Pasca, M., Shen, W., Wu, F., Miao, G., & Wu, C.\n\n\n \n\n\n\n Proc. VLDB Endow., 4(9): 528–538. 2011.\n \n\n\n\n
\n\n\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/pvldb/VenetisHMPSWMW11,\n\tauthor    = {Petros Venetis and\n\tAlon Y. Halevy and\n\tJayant Madhavan and\n\tMarius Pasca and\n\tWarren Shen and\n\tFei Wu and\n\tGengxin Miao and\n\tChung Wu},\n\ttitle     = {Recovering Semantics of Tables on the Web},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {4},\n\tnumber    = {9},\n\tpages     = {528--538},\n\tyear      = {2011}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2010\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Annotating and Searching Web Tables Using Entities, Types and Relationships.\n \n \n \n\n\n \n Limaye, G., Sarawagi, S., & Chakrabarti, S.\n\n\n \n\n\n\n Proc. VLDB Endow., 3(1): 1338–1347. 2010.\n \n\n\n\n
\n\n\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/pvldb/LimayeSC10,\n\tauthor    = {Girija Limaye and\n\tSunita Sarawagi and\n\tSoumen Chakrabarti},\n\ttitle     = {Annotating and Searching Web Tables Using Entities, Types and Relationships},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {3},\n\tnumber    = {1},\n\tpages     = {1338--1347},\n\tyear      = {2010}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n On indexing error-tolerant set containment.\n \n \n \n\n\n \n Agrawal, P., Arasu, A., & Kaushik, R.\n\n\n \n\n\n\n In SIGMOD, pages 927–938, 2010. \n \n\n\n\n
\n\n\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/sigmod/AgrawalAK10,\n  author    = {Parag Agrawal and\n               Arvind Arasu and\n               Raghav Kaushik},\n  title     = {On indexing error-tolerant set containment},\n  booktitle = {{SIGMOD}},\n  pages     = {927--938},\n  year      = {2010}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2009\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Data Integration for the Relational Web.\n \n \n \n\n\n \n Cafarella, M. J., Halevy, A. Y., & Khoussainova, N.\n\n\n \n\n\n\n Proc. VLDB Endow., 2(1): 1090–1101. 2009.\n \n\n\n\n
\n\n\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/pvldb/CafarellaHK09,\n\tauthor    = {Michael J. Cafarella and\n\tAlon Y. Halevy and\n\tNodira Khoussainova},\n\ttitle     = {Data Integration for the Relational Web},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {2},\n\tnumber    = {1},\n\tpages     = {1090--1101},\n\tyear      = {2009}\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2008\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n WebTables: exploring the power of tables on the web.\n \n \n \n\n\n \n Cafarella, M. J., Halevy, A. Y., Wang, D. Z., Wu, E., & Zhang, Y.\n\n\n \n\n\n\n Proc. VLDB Endow., 1(1): 538–549. 2008.\n \n\n\n\n
\n\n\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/pvldb/CafarellaHWWZ08,\n\tauthor    = {Michael J. Cafarella and\n\tAlon Y. Halevy and\n\tDaisy Zhe Wang and\n\tEugene Wu and\n\tYang Zhang},\n\ttitle     = {WebTables: exploring the power of tables on the web},\n\tjournal   = {Proc. {VLDB} Endow.},\n\tvolume    = {1},\n\tnumber    = {1},\n\tpages     = {538--549},\n\tyear      = {2008}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2004\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Locality-sensitive hashing scheme based on p-stable distributions.\n \n \n \n\n\n \n Datar, M., Immorlica, N., Indyk, P., & Mirrokni, V. S.\n\n\n \n\n\n\n In SCG, pages 253–262, 2004. ACM\n \n\n\n\n
\n\n\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/compgeom/DatarIIM04,\n  author    = {Mayur Datar and\n               Nicole Immorlica and\n               Piotr Indyk and\n               Vahab S. Mirrokni},\n  title     = {Locality-sensitive hashing scheme based on p-stable distributions},\n  booktitle = {{SCG}},\n  pages     = {253--262},\n  publisher = {{ACM}},\n  year      = {2004}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2002\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n DISCOVER: Keyword Search in Relational Databases.\n \n \n \n\n\n \n Hristidis, V., & Papakonstantinou, Y.\n\n\n \n\n\n\n In VLDB, pages 670–681, 2002. \n \n\n\n\n
\n\n\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/vldb/HristidisP02,\n  author    = {Vagelis Hristidis and\n               Yannis Papakonstantinou},\n  title     = {{DISCOVER:} Keyword Search in Relational Databases},\n  booktitle = {VLDB},\n  pages     = {670--681},\n  year      = {2002}\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);