{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T02:54:47Z","timestamp":1764557687945,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,21]]},"DOI":"10.1145\/3583780.3614750","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:26Z","timestamp":1697874326000},"page":"5096-5100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["NumJoin: Discovering Numeric Joinable Tables with Semantically Related Columns"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4684-0501","authenticated-orcid":false,"given":"Pranav","family":"Subramaniam","sequence":"first","affiliation":[{"name":"The University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8113-1210","authenticated-orcid":false,"given":"Udayan","family":"Khurana","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4610-967X","authenticated-orcid":false,"given":"Kavitha","family":"Srinivas","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6780-3217","authenticated-orcid":false,"given":"Horst","family":"Samulowitz","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Dataset Discovery in Data Lakes. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 709--720","author":"Bogatu Alex","year":"2020","unstructured":"Alex Bogatu , Alvaro A. A. Fernandes , Norman W. Paton , and Nikolaos Konstantinou . 2020 . Dataset Discovery in Data Lakes. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 709--720 . https:\/\/doi.org\/10.1109\/ICDE48307.2020.00067 10.1109\/ICDE48307.2020.00067 Alex Bogatu, Alvaro A. A. Fernandes, Norman W. Paton, and Nikolaos Konstantinou. 2020. Dataset Discovery in Data Lakes. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 709--720. https:\/\/doi.org\/10.1109\/ICDE48307.2020.00067"},{"key":"e_1_3_2_1_2_1","volume-title":"Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). 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 . 2018 . Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). 989--1000 . https:\/\/doi.org\/10.1109\/ICDE.2018.00093 10.1109\/ICDE.2018.00093 Raul Castro Fernandez, Essam Mansour, Abdulhakim A. Qahtan, Ahmed Elmagarmid, Ihab Ilyas, Samuel Madden, Mourad Ouzzani, Michael Stonebraker, and Nan Tang. 2018. Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). 989--1000. https:\/\/doi.org\/10.1109\/ICDE.2018.00093"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397235"},{"key":"e_1_3_2_1_4_1","volume-title":"Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach. CoRR","author":"Dong Yuyang","year":"2020","unstructured":"Yuyang Dong , Kunihiro Takeoka , Chuan Xiao , and Masafumi Oyamada . 2020. Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach. CoRR , Vol. abs\/ 2010 .13273 ( 2020 ). showeprint[arXiv]2010.13273 https:\/\/arxiv.org\/abs\/2010.13273 Yuyang Dong, Kunihiro Takeoka, Chuan Xiao, and Masafumi Oyamada. 2020. Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach. CoRR, Vol. abs\/2010.13273 (2020). showeprint[arXiv]2010.13273 https:\/\/arxiv.org\/abs\/2010.13273"},{"key":"#cr-split#-e_1_3_2_1_5_1.1","doi-asserted-by":"crossref","unstructured":"Yuyang Dong Chuan Xiao Takuma Nozawa Masafumi Enomoto and Masafumi Oyamada. 2022. DeepJoin: Joinable Table Discovery with Pre-trained Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2212.07588 10.48550\/ARXIV.2212.07588","DOI":"10.14778\/3603581.3603587"},{"key":"#cr-split#-e_1_3_2_1_5_1.2","doi-asserted-by":"crossref","unstructured":"Yuyang Dong Chuan Xiao Takuma Nozawa Masafumi Enomoto and Masafumi Oyamada. 2022. DeepJoin: Joinable Table Discovery with Pre-trained Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2212.07588","DOI":"10.14778\/3603581.3603587"},{"key":"e_1_3_2_1_6_1","volume-title":"MATE: Multi-Attribute Table Extraction. CoRR","author":"Esmailoghli Mahdi","year":"2021","unstructured":"Mahdi Esmailoghli , Jorge-Arnulfo Quian\u00e9 -Ruiz , and Ziawasch Abedjan . 2021 a. MATE: Multi-Attribute Table Extraction. CoRR , Vol. abs\/ 2110 .00318 (2021). showeprint[arXiv]2110.00318 https:\/\/arxiv.org\/abs\/2110.00318 Mahdi Esmailoghli, Jorge-Arnulfo Quian\u00e9 -Ruiz, and Ziawasch Abedjan. 2021a. MATE: Multi-Attribute Table Extraction. CoRR, Vol. abs\/2110.00318 (2021). showeprint[arXiv]2110.00318 https:\/\/arxiv.org\/abs\/2110.00318"},{"key":"e_1_3_2_1_7_1","volume-title":"COCOA: COrrelation COefficient-Aware Data Augmentation. In EDBT.","author":"Esmailoghli Mahdi","year":"2021","unstructured":"Mahdi Esmailoghli , Jorge-Arnulfo Quian\u00e9-Ruiz , and Ziawasch Abedjan . 2021 b. COCOA: COrrelation COefficient-Aware Data Augmentation. In EDBT. Mahdi Esmailoghli, Jorge-Arnulfo Quian\u00e9-Ruiz, and Ziawasch Abedjan. 2021b. COCOA: COrrelation COefficient-Aware Data Augmentation. In EDBT."},{"key":"#cr-split#-e_1_3_2_1_8_1.1","unstructured":"Grace Fan Jin Wang Yuliang Li Dan Zhang and Ren\u00e9e Miller. 2022. Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning. https:\/\/doi.org\/10.48550\/ARXIV.2210.01922 10.48550\/ARXIV.2210.01922"},{"key":"#cr-split#-e_1_3_2_1_8_1.2","doi-asserted-by":"crossref","unstructured":"Grace Fan Jin Wang Yuliang Li Dan Zhang and Ren\u00e9e Miller. 2022. Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning. https:\/\/doi.org\/10.48550\/ARXIV.2210.01922","DOI":"10.14778\/3587136.3587146"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/ios.SW121S1"},{"key":"e_1_3_2_1_10_1","volume-title":"SANTOS: Relationship-based Semantic Table Union Search. https:\/\/doi.org\/10.48550\/ARXIV.2209.13589","author":"Khatiwada Aamod","year":"2022","unstructured":"Aamod Khatiwada , Grace Fan , Roee Shraga , Zixuan Chen , Wolfgang Gatterbauer , Ren\u00e9e J. Miller , and Mirek Riedewald . 2022 . SANTOS: Relationship-based Semantic Table Union Search. https:\/\/doi.org\/10.48550\/ARXIV.2209.13589 10.48550\/ARXIV.2209.13589 Aamod Khatiwada, Grace Fan, Roee Shraga, Zixuan Chen, Wolfgang Gatterbauer, Ren\u00e9e J. Miller, and Mirek Riedewald. 2022. SANTOS: Relationship-based Semantic Table Union Search. https:\/\/doi.org\/10.48550\/ARXIV.2209.13589"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482295"},{"key":"#cr-split#-e_1_3_2_1_12_1.1","unstructured":"Udayan Khurana Kavitha Srinivas and Horst Samulowitz. 2022. A Survey on Semantics in Automated Data Science. https:\/\/doi.org\/10.48550\/ARXIV.2205.08018 10.48550\/ARXIV.2205.08018"},{"key":"#cr-split#-e_1_3_2_1_12_1.2","unstructured":"Udayan Khurana Kavitha Srinivas and Horst Samulowitz. 2022. A Survey on Semantics in Automated Data Science. https:\/\/doi.org\/10.48550\/ARXIV.2205.08018"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452824"},{"key":"e_1_3_2_1_14_1","unstructured":"Dan Ofer. 2019. DBPedia Classes: Hierarchical Taxonomy of Wikipedia article classes. https:\/\/www.kaggle.com\/datasets\/danofer\/dbpedia-classes  Dan Ofer. 2019. DBPedia Classes: Hierarchical Taxonomy of Wikipedia article classes. https:\/\/www.kaggle.com\/datasets\/danofer\/dbpedia-classes"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494149"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301281"},{"volume-title":"Proceedings of the 2019 International Conference on Management of Data","author":"Zhu Erkang","key":"e_1_3_2_1_17_1","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 ( Amsterdam, Netherlands) (SIGMOD '19). Association for Computing Machinery, New York, NY, USA, 847--864. https:\/\/doi.org\/10.1145\/3299869.3300065 10.1145\/3299869.3300065 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 (Amsterdam, Netherlands) (SIGMOD '19). Association for Computing Machinery, New York, NY, USA, 847--864. https:\/\/doi.org\/10.1145\/3299869.3300065"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115409"},{"key":"e_1_3_2_1_19_1","first-page":"12","article-title":"LSH Ensemble","volume":"9","author":"Zhu Erkang","year":"2016","unstructured":"Erkang Zhu , Fatemeh Nargesian , Ken Q. Pu , and Ren\u00e9e J. Miller . 2016 . LSH Ensemble : Internet-Scale Domain Search. Proc. VLDB Endow. , Vol. 9 , 12 (aug 2016), 1185--1196. https:\/\/doi.org\/10.14778\/2994509.2994534 10.14778\/2994509.2994534 Erkang Zhu, Fatemeh Nargesian, Ken Q. Pu, and Ren\u00e9e J. Miller. 2016. LSH Ensemble: Internet-Scale Domain Search. Proc. VLDB Endow., Vol. 9, 12 (aug 2016), 1185--1196. https:\/\/doi.org\/10.14778\/2994509.2994534","journal-title":"Internet-Scale Domain Search. Proc. VLDB Endow."}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3614750","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3614750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:30Z","timestamp":1750178790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3614750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":22,"alternative-id":["10.1145\/3583780.3614750","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3614750","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}