{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T20:02:57Z","timestamp":1779825777264,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,31]]},"DOI":"10.1145\/3788853.3801605","type":"proceedings-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:14:47Z","timestamp":1779822887000},"page":"106-109","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Intent-aware Join Discovery using Natural Language"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9314-7793","authenticated-orcid":false,"given":"Mir Mahathir","family":"Mohammad","sequence":"first","affiliation":[{"name":"University of Utah, Salt Lake City, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-3499","authenticated-orcid":false,"given":"El Kindi","family":"Rezig","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. The Home of the U.S. Government's Open Data. https:\/\/data.gov\/."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. NLDisc demo video. https:\/\/youtu.be\/QRPtM5aWiS8"},{"key":"e_1_3_2_1_3_1","volume-title":"BEAVER: an enterprise benchmark for text-to-sql. arXiv preprint arXiv:2409.02038","author":"Chen Peter Baile","year":"2024","unstructured":"Peter Baile Chen, FabianWenz, Yi Zhang, Devin Yang, Justin Choi, Nesime Tatbul, Michael Cafarella, \u00c7a\u011fatay Demiralp, and Michael Stonebraker. 2024. BEAVER: an enterprise benchmark for text-to-sql. arXiv preprint arXiv:2409.02038 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses. In 13th Conference on Innovative Data Systems Research, CIDR 2023","author":"Cong Tianji","year":"2023","unstructured":"Tianji Cong, James Gale, Jason Frantz, H. V. Jagadish, and \u00c7agatay Demiralp. 2023. WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses. In 13th Conference on Innovative Data Systems Research, CIDR 2023, Amsterdam, The Netherlands, January 8-11, 2023. www.cidrdb.org."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3659437.3659448"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3603581.3603587"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681960"},{"key":"e_1_3_2_1_8_1","volume-title":"2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, ICDE, ICDE, 1001-1012","author":"Fernandez Raul Castro","year":"2018","unstructured":"Raul Castro Fernandez, Ziawasch Abedjan, Famien Koko, Gina Yuan, Samuel Madden, and Michael Stonebraker. 2018. Aurum: A data discovery system. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, ICDE, ICDE, 1001-1012."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3786682"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476353"},{"key":"e_1_3_2_1_12_1","unstructured":"Aaditya Singh Adam Fry Adam Perelman Adam Tart Adi Ganesh Ahmed El-Kishky Aidan McLaughlin Aiden Low AJ Ostrow Akhila Ananthram et al. 2025. Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Song Kaitao","year":"2020","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. MPNet: masked and permuted pre-training for language understanding. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 1414, 11 pages."},{"key":"e_1_3_2_1_14_1","volume-title":"D1","author":"Ursu Oleg","year":"2019","unstructured":"Oleg Ursu, Jayme Holmes, Cristian G Bologa, Jeremy J Yang, Stephen L Mathias, Vasileios Stathias, Dac-Trung Nguyen, Stephan Sch\u00fcrer, and Tudor Oprea. 2019. DrugCentral 2018: an update. Nucleic acids research 47, D1 (2019), D963-D970."},{"key":"e_1_3_2_1_15_1","unstructured":"Qiming Wang and Raul Castro Fernandez. [n.d.]. Solo: Data Discovery Using Natural Language Questions Via A Self-Supervised Approach. SIGMOD ([n.d.])."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Tao Yu Rui Zhang Kai Yang Michihiro Yasunaga Dongxu Wang Zifan Li James Ma Irene Li Qingning Yao Shanelle Roman Zilin Zhang and Dragomir Radev. 2018. Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff David Chiang Julia Hockenmaier and Jun'ichi Tsujii (Eds.). Association for Computational Linguistics Brussels Belgium 3911-3921. doi:10.18653\/v1\/D18-1425","DOI":"10.18653\/v1\/D18-1425"}],"event":{"name":"SIGMOD\/PODS '26: International Conference on Management of Data","location":"Bengaluru India","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the International Conference on Management of Data"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:18:04Z","timestamp":1779823084000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788853.3801605"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":16,"alternative-id":["10.1145\/3788853.3801605","10.1145\/3788853"],"URL":"https:\/\/doi.org\/10.1145\/3788853.3801605","relation":{},"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"2026-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}