{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:00:08Z","timestamp":1775638808083,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ARC Discovery Project","award":["DP190102141"],"award-info":[{"award-number":["DP190102141"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583515","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:25Z","timestamp":1682551825000},"page":"3859-3867","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Human-in-the-loop Regular Expression Extraction for Single Column Format Inconsistency"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4526-1525","authenticated-orcid":false,"given":"Shaochen","family":"Yu","sequence":"first","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7777-3592","authenticated-orcid":false,"given":"Lei","family":"Han","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2156-4097","authenticated-orcid":false,"given":"Marta","family":"Indulska","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6739-4145","authenticated-orcid":false,"given":"Shazia","family":"Sadiq","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7311-3693","authenticated-orcid":false,"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31280-0_2"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1871840.1871848"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.46"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2515587"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063763"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858411"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749431"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2676726.2676973"},{"key":"e_1_3_2_2_9_1","volume-title":"Exploratory data mining and data cleaning","author":"Dasu Tamraparni","unstructured":"Tamraparni Dasu and Theodore Johnson. 2003. Exploratory data mining and data cleaning. John Wiley & Sons."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ic.2008.12.008"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2015.66"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1925844.1926423"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401059"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Ihab\u00a0F Ilyas and Xu Chu. 2019. Data cleaning. Morgan & Claypool.","DOI":"10.1145\/3310205"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064034"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_2_17_1","volume-title":"International Colloquium on Grammatical Inference","author":"Kinber Efim","unstructured":"Efim Kinber. 2010. Learning regular expressions from representative examples and membership queries. In International Colloquium on Grammatical Inference. Springer, 94\u2013108."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939511"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993236.2993244"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613719"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35063-4_33"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2590989.2590995"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360565"},{"key":"e_1_3_2_2_24_1","unstructured":"Vijayshankar Raman and Joseph\u00a0M Hellerstein. 2001. Potter\u2019s wheel: An interactive data cleaning system. In VLDB Vol.\u00a01. 381\u2013390."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93037-4_6"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816736"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479592"},{"key":"e_1_3_2_2_28_1","volume-title":"23rd { USENIX} Security Symposium ({ USENIX} Security 14). 239\u2013254.","author":"Wang Gang","unstructured":"Gang Wang, Tianyi Wang, Haitao Zheng, and Ben\u00a0Y Zhao. 2014. Man vs. machine: Practical adversarial detection of malicious crowdsourcing workers. In 23rd { USENIX} Security Symposium ({ USENIX} Security 14). 239\u2013254."},{"key":"e_1_3_2_2_29_1","volume-title":"Crowder: Crowdsourcing entity resolution. arXiv preprint arXiv:1208.1927","author":"Wang Jiannan","year":"2012","unstructured":"Jiannan Wang, Tim Kraska, Michael\u00a0J Franklin, and Jianhua Feng. 2012. Crowder: Crowdsourcing entity resolution. arXiv preprint arXiv:1208.1927 (2012)."},{"key":"e_1_3_2_2_30_1","volume-title":"DataOps-4G: On Supporting Generalists in Data Quality Discovery","author":"Yu Shaochen","year":"2022","unstructured":"Shaochen Yu, Tianwa Chen, Lei Han, Gianluca Demartini, and Shazia Sadiq. 2022. DataOps-4G: On Supporting Generalists in Data Quality Discovery. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_3_2_2_31_1","volume-title":"Data preparation for data mining. Applied artificial intelligence 17, 5-6","author":"Zhang Shichao","year":"2003","unstructured":"Shichao Zhang, Chengqi Zhang, and Qiang Yang. 2003. Data preparation for data mining. Applied artificial intelligence 17, 5-6 (2003), 375\u2013381."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583515","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:02Z","timestamp":1750178822000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":31,"alternative-id":["10.1145\/3543507.3583515","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583515","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}