{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:15:38Z","timestamp":1764656138298,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"IITP by the Korea government (MSIT)","award":["2019-0-01343, 2019-0-00421"],"award-info":[{"award-number":["2019-0-01343, 2019-0-00421"]}]},{"name":"NRF of Korea by the MSIT","award":["2019M3F2A1072217), 2017R1C1B5076474, 2020R1C1C1006004"],"award-info":[{"award-number":["2019M3F2A1072217), 2017R1C1B5076474, 2020R1C1C1006004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,3,22]]},"DOI":"10.1145\/3412841.3441969","type":"proceedings-article","created":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T05:09:42Z","timestamp":1619154582000},"page":"942-951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["BertLoc"],"prefix":"10.1145","author":[{"given":"Sujin","family":"Park","sequence":"first","affiliation":[{"name":"Sungkyunkwan University, South Korea"}]},{"given":"Sangwon","family":"Lee","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, South Korea"}]},{"given":"Simon S.","family":"Woo","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2021,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956759"},{"key":"e_1_3_2_1_2_1","first-page":"73","article-title":"A Comparison of String Distance Metrics for Name-Matching Tasks","volume":"2003","author":"Cohen William W","year":"2003","unstructured":"William W Cohen, Pradeep Ravikumar, Stephen E Fienberg, et al. 2003. A Comparison of String Distance Metrics for Name-Matching Tasks.. In IIWeb, Vol. 2003. 73--78.","journal-title":"IIWeb"},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.250581"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952551"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/568271.223807"},{"volume-title":"Soviet physics doklady","author":"Levenshtein Vladimir I","key":"e_1_3_2_1_8_1","unstructured":"Vladimir I Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, Vol. 10. 707--710."},{"key":"e_1_3_2_1_9_1","volume-title":"Matthew Wiener, et al","author":"Liaw Andy","year":"2002","unstructured":"Andy Liaw, Matthew Wiener, et al. 2002. Classification and regression by randomForest. R news 2, 3 (2002), 18--22."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20630-6_3"},{"key":"e_1_3_2_1_11_1","volume-title":"7th Iberian Conference on Information Systems and Technologies (CISTI","author":"Martins Bruno","year":"2012","unstructured":"Bruno Martins, Helena Galhardas, and Nelson Gon\u00e7alves. 2012. Using Random Forest classifiers to detect duplicate gazetteer records. In 7th Iberian Conference on Information Systems and Technologies (CISTI 2012). IEEE, 1--4."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347123"},{"key":"e_1_3_2_1_13_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_14_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1214\/088342306000000493"},{"key":"e_1_3_2_1_16_1","first-page":"267","article-title":"The Field Matching Problem: Algorithms and Applications","volume":"2","author":"Monge Alvaro E","year":"1996","unstructured":"Alvaro E Monge, Charles Elkan, et al. 1996. The Field Matching Problem: Algorithms and Applications.. In Kdd, Vol. 2. 267--270.","journal-title":"Kdd"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196926"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the international multiconference of engineers and computer scientists","volume":"1","author":"Niwattanakul Suphakit","year":"2013","unstructured":"Suphakit Niwattanakul, Jatsada Singthongchai, Ekkachai Naenudorn, and Supachanun Wanapu. 2013. Using of Jaccard coefficient for keywords similarity. In Proceedings of the international multiconference of engineers and computer scientists, Vol. 1. 380--384."},{"key":"e_1_3_2_1_19_1","unstructured":"Mohammad Norouzi David J Fleet and Russ R Salakhutdinov. 2012. Hamming distance metric learning. In Advances in neural information processing systems. 1061--1069."},{"key":"e_1_3_2_1_20_1","unstructured":"Hanna Pasula Bhaskara Marthi Brian Milch Stuart J Russell and Ilya Shpitser. 2003. Identity uncertainty and citation matching. In Advances in neural information processing systems. 1425--1432."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12145-019-00390-3"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1390119"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775087"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183471.1183486"},{"key":"e_1_3_2_1_26_1","volume-title":"Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909","author":"Sennrich Rico","year":"2015","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2015. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)."},{"key":"e_1_3_2_1_27_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"volume-title":"Overview of record linkage and current research directions","author":"Winkler William E","key":"e_1_3_2_1_28_1","unstructured":"William E Winkler. 2006. Overview of record linkage and current research directions. In Bureau of the Census. Citeseer."},{"key":"e_1_3_2_1_29_1","volume-title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv abs\/1910.03771","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R'emi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv abs\/1910.03771 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313578"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869812"}],"event":{"name":"SAC '21: The 36th ACM\/SIGAPP Symposium on Applied Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"location":"Virtual Event Republic of Korea","acronym":"SAC '21"},"container-title":["Proceedings of the 36th Annual ACM Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3412841.3441969","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3412841.3441969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:24Z","timestamp":1750197744000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3412841.3441969"}},"subtitle":["duplicate location record detection in a large-scale location dataset"],"short-title":[],"issued":{"date-parts":[[2021,3,22]]},"references-count":31,"alternative-id":["10.1145\/3412841.3441969","10.1145\/3412841"],"URL":"https:\/\/doi.org\/10.1145\/3412841.3441969","relation":{},"subject":[],"published":{"date-parts":[[2021,3,22]]},"assertion":[{"value":"2021-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}