{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T23:46:34Z","timestamp":1785714394508,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"DITDP","award":["JCKY2021211B017"],"award-info":[{"award-number":["JCKY2021211B017"]}]},{"name":"NSFC","award":["61932004, 62225203, U21A20516"],"award-info":[{"award-number":["61932004, 62225203, U21A20516"]}]},{"name":"National Key R&D Program of China","award":["2022YFB2702100"],"award-info":[{"award-number":["2022YFB2702100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591637","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"770-780","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["An Effective Framework for Enhancing Query Answering in a Heterogeneous Data Lake"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7123-6155","authenticated-orcid":false,"given":"Qin","family":"Yuan","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0247-9866","authenticated-orcid":false,"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2914-912X","authenticated-orcid":false,"given":"Zhenyu","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1080-6406","authenticated-orcid":false,"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1014-0659","authenticated-orcid":false,"given":"Shiyuan","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Azure Synapse Analytics. https:\/\/azure.microsoft.com\/en-us\/services\/ synapse-analytics\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/1325851.1325900"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415545"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323878.3325804"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3085504.3091116"},{"key":"e_1_3_2_1_6_1","first-page":"14","article-title":"Enabling JSON Document Stores in Relational Systems","volume":"13","author":"Chasseur Craig","year":"2013","unstructured":"Craig Chasseur, Yinan Li, and Jignesh M Patel. 2013. Enabling JSON Document Stores in Relational Systems.. In WebDB, Vol. 13. 14--15.","journal-title":"WebDB"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903741"},{"key":"e_1_3_2_1_8_1","volume-title":"Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed K Elmagarmid, Ihab F Ilyas, Samuel Madden, Mourad Ouzzani, and Nan Tang.","author":"Deng Dong","year":"2017","unstructured":"Dong Deng, Raul Castro Fernandez, Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed K Elmagarmid, Ihab F Ilyas, Samuel Madden, Mourad Ouzzani, and Nan Tang. 2017. The Data Civilizer System.. In Cidr."},{"key":"e_1_3_2_1_9_1","volume-title":"Storing Semistructured Data with STORED. In SIGMOD 1999, Proceedings ACM SIGMOD International Conference on Management of Data","author":"Deutsch Alin","year":"1999","unstructured":"Alin Deutsch, Mary F. Fern\u00e1 ndez, and Dan Suciu. 1999. Storing Semistructured Data with STORED. In SIGMOD 1999, Proceedings ACM SIGMOD International Conference on Management of Data, June 1-3, 1999, Philadelphia, Pennsylvania, USA, Alex Delis, Christos Faloutsos, and Shahram Ghandeharizadeh (Eds.). ACM Press, 431--442."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882924"},{"key":"e_1_3_2_1_11_1","volume-title":"Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach. In 37th IEEE International Conference on Data Engineering, ICDE 2021","author":"Dong Yuyang","year":"2021","unstructured":"Yuyang Dong, Kunihiro Takeoka, Chuan Xiao, and Masafumi Oyamada. 2021. Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach. In 37th IEEE International Conference on Data Engineering, ICDE 2021, Chania, Greece, April 19-22, 2021. IEEE, 456--467."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806557"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.21782"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236198"},{"key":"e_1_3_2_1_15_1","unstructured":"J\u00e9r\u00f4me Euzenat Pavel Shvaiko et al. 2007. Ontology matching. Vol. 18. Springer."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00094"},{"key":"e_1_3_2_1_17_1","volume-title":"2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, 989--1000","author":"Fernandez Raul Castro","year":"2018","unstructured":"Raul Castro Fernandez, Essam Mansour, Abdulhakim A Qahtan, Ahmed Elmagarmid, Ihab Ilyas, Samuel Madden, Mourad Ouzzani, Michael Stonebraker, and Nan Tang. 2018b. Seeping semantics: Linking datasets using word embeddings for data discovery. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, 989--1000."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840636"},{"key":"e_1_3_2_1_19_1","first-page":"19","article-title":"The Cascades Framework for Query Optimization","volume":"18","author":"Graefe Goetz","year":"1995","unstructured":"Goetz Graefe. 1995. The Cascades Framework for Query Optimization. IEEE Data Eng. Bull., Vol. 18, 3 (1995), 19--29.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295822"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2899389"},{"key":"e_1_3_2_1_22_1","volume-title":"Data lake concept and systems: a survey. arXiv preprint arXiv:2106.09592","author":"Hai Rihan","year":"2021","unstructured":"Rihan Hai, Christoph Quix, and Matthias Jarke. 2021. Data lake concept and systems: a survey. arXiv preprint arXiv:2106.09592 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Ground: A Data Context Service. In 8th Biennial Conference on Innovative Data Systems Research, CIDR 2017, Chaminade, CA, USA, January 8-11, 2017, Online Proceedings.","author":"Hellerstein Joseph M.","year":"2017","unstructured":"Joseph M. Hellerstein, Vikram Sreekanti, Joseph E. Gonzalez, James Dalton, Akon Dey, Sreyashi Nag, Krishna Ramachandran, Sudhanshu Arora, Arka Bhattacharyya, Shirshanka Das, Mark Donsky, Gabriel Fierro, Chang She, Carl Steinbach, Venkat Subramanian, and Eric Sun. 2017. Ground: A Data Context Service. In 8th Biennial Conference on Innovative Data Systems Research, CIDR 2017, Chaminade, CA, USA, January 8-11, 2017, Online Proceedings."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574274"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1072"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983801"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196926"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, online conference [Portland, OR, USA]","author":"Nargesian Fatemeh","year":"2020","unstructured":"Fatemeh Nargesian, Ken Q. Pu, Erkang Zhu, Bahar Ghadiri Bashardoost, and Ren\u00e9e J. Miller. 2020. Organizing Data Lakes for Navigation. In Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, online conference [Portland, OR, USA], June 14-19, 2020, David Maier, Rachel Pottinger, AnHai Doan, Wang-Chiew Tan, Abdussalam Alawini, and Hung Q. Ngo (Eds.). 1939--1950."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352116"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3192965.3192973"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.08.032"},{"key":"e_1_3_2_1_34_1","volume-title":"Dldb: Extending relational databases to support semantic web queries. Technical Report. LEHIGH UNIV BETHLEHEM PA DEPT OF COMPUTER SCIENCE AND ELECTRICAL ENGINEERING.","author":"Pan Zhengxiang","year":"2004","unstructured":"Zhengxiang Pan and Jeff Heflin. 2004. Dldb: Extending relational databases to support semantic web queries. Technical Report. LEHIGH UNIV BETHLEHEM PA DEPT OF COMPUTER SCIENCE AND ELECTRICAL ENGINEERING."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46523-4_28"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00196"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2012","author":"Shankar Srinath","year":"2012","unstructured":"Srinath Shankar, Rimma V. Nehme, Josep Aguilar-Saborit, Andrew Chung, Mostafa Elhemali, Alan Halverson, Eric Robinson, Mahadevan Sankara Subramanian, David J. DeWitt, and C\u00e9sar A. Galindo-Legaria. 2012. Query optimization in microsoft SQL server PDW. In Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2012, Scottsdale, AZ, USA, May 20-24, 2012, K. Sel\u00e7uk Candan, Yi Chen, Richard T. Snodgrass, Luis Gravano, and Ariel Fuxman (Eds.). ACM, 767--776."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397237"},{"key":"e_1_3_2_1_39_1","volume-title":"Cidr","volume":"2013","author":"Stonebraker Michael","year":"2013","unstructured":"Michael Stonebraker, Daniel Bruckner, Ihab F Ilyas, George Beskales, Mitch Cherniack, Stanley B Zdonik, Alexander Pagan, and Shan Xu. 2013. Data curation at scale: the data tamer system.. In Cidr, Vol. 2013."},{"key":"e_1_3_2_1_40_1","volume-title":"Probabilistic databases. Synthesis lectures on data management","author":"Suciu Dan","year":"2011","unstructured":"Dan Suciu, Dan Olteanu, Christopher R\u00e9, and Christoph Koch. 2011. Probabilistic databases. Synthesis lectures on data management, Vol. 3, 2 (2011), 1--180."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386134"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2612183"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564715"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401146"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213848"},{"key":"e_1_3_2_1_47_1","volume-title":"Linking semistructured data on the web. Interface","author":"Yeganeh S Hassas","year":"2011","unstructured":"S Hassas Yeganeh, Oktie Hassanzadeh, and Ren\u00e9e J Miller. 2011. Linking semistructured data on the web. Interface (2011)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482191"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12026-8_14"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.14778\/2311906.2311908"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.222"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402726"},{"key":"e_1_3_2_1_53_1","volume-title":"Neural Motifs: Scene Graph Parsing With Global Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Zellers Rowan","year":"2018","unstructured":"Rowan Zellers, Mark Yatskar, Sam Thomson, and Yejin Choi. 2018. Neural Motifs: Scene Graph Parsing With Global Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. Computer Vision Foundation \/ IEEE Computer Society, 5831--5840."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the VLDB 2018 PhD Workshop co-located with the 44th International Conference on Very Large Databases (VLDB 2018","author":"Zhang Chao","year":"2018","unstructured":"Chao Zhang. 2018. Parameter Curation and Data Generation for Benchmarking Multi-model Queries. In Proceedings of the VLDB 2018 PhD Workshop co-located with the 44th International Conference on Very Large Databases (VLDB 2018), Rio de Janeiro, Brasil, Aug 27-31, 2018, Senjuti Basu Roy and Altigran Soares da Silva (Eds.), Vol. 2175."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989336"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, online conference [Portland, OR, USA]","author":"Zhang Yi","year":"2020","unstructured":"Yi Zhang and Zachary G. Ives. 2020. Finding Related Tables in Data Lakes for Interactive Data Science. In Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, online conference [Portland, OR, USA], June 14-19, 2020. ACM, 1951--1966."},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 2019 International Conference on Management of Data, SIGMOD Conference 2019","author":"Zhu Erkang","year":"2019","unstructured":"Erkang Zhu, Dong Deng, Fatemeh Nargesian, and Ren\u00e9e J. Miller. 2019. JOSIE: Overlap Set Similarity Search for Finding Joinable Tables in Data Lakes. In Proceedings of the 2019 International Conference on Management of Data, SIGMOD Conference 2019, Amsterdam, The Netherlands, June 30 - July 5, 2019, Peter A. Boncz, Stefan Manegold, Anastasia Ailamaki, Amol Deshpande, and Tim Kraska (Eds.). 847--864."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591637","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":57,"alternative-id":["10.1145\/3539618.3591637","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591637","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}