{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:00:07Z","timestamp":1775638807447,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,3,24]],"date-time":"2009-03-24T00:00:00Z","timestamp":1237852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002994","name":"Ministry of Knowledge Economy","doi-asserted-by":"publisher","award":["IITA-2008-C1090-0801-0031"],"award-info":[{"award-number":["IITA-2008-C1090-0801-0031"]}],"id":[{"id":"10.13039\/501100002994","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,3,24]]},"DOI":"10.1145\/1516360.1516455","type":"proceedings-article","created":{"date-parts":[[2009,4,6]],"date-time":"2009-04-06T16:34:53Z","timestamp":1239035693000},"page":"827-838","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Approximate substring selectivity estimation"],"prefix":"10.1145","author":[{"given":"Hongrae","family":"Lee","sequence":"first","affiliation":[{"name":"University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond T.","family":"Ng","sequence":"additional","affiliation":[{"name":"University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyuseok","family":"Shim","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2009,3,24]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"918","volume-title":"Proc. VLDB","author":"Arasu A.","year":"2006","unstructured":"A. Arasu , V. Ganti , R. Kaushik . Efficient Exact Set-Similarity Joins . Proc. VLDB , pp. 918 -- 929 , 2006 . A. Arasu, V. Ganti, R. Kaushik. Efficient Exact Set-Similarity Joins. Proc. VLDB, pp. 918--929, 2006."},{"key":"e_1_3_2_1_2_1","volume-title":"Modern Information Retrieval","author":"Baeza-Yates R.","year":"1999","unstructured":"R. Baeza-Yates and B. A. Ribeiro-Neto . Modern Information Retrieval . ACM Press\/Addison-Wesley , 1999 . R. Baeza-Yates and B. A. Ribeiro-Neto. Modern Information Retrieval. ACM Press\/Addison-Wesley, 1999."},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. Compression and Complexity of SEQUENCES","author":"Andrei","year":"1997","unstructured":"Andrei Z. Broder, On the resemblance and containment of documents , Proc. Compression and Complexity of SEQUENCES , 1997 . Andrei Z. Broder, On the resemblance and containment of documents, Proc. Compression and Complexity of SEQUENCES, 1997."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1999.1690"},{"key":"e_1_3_2_1_5_1","first-page":"227","volume-title":"Proc. ICDE","author":"Chaudhuri S.","year":"2004","unstructured":"S. Chaudhuri , V. Ganti and L. Gravano . Selectivity Estimation for String Predicates: Overcoming the Underestimation Problem . Proc. ICDE , pp. 227 -- 238 , 2004 . S. Chaudhuri, V. Ganti and L. Gravano. Selectivity Estimation for String Predicates: Overcoming the Underestimation Problem. Proc. ICDE, pp. 227--238, 2004."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242524.1242529"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872796"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/335168.335225"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1534"},{"key":"e_1_3_2_1_10_1","first-page":"73","volume-title":"P. Ravikmar and and S. Fienberg. A Comparison of String Metrics for Matching Names and Records. Proc. of KDD Workshop on Data Cleaning","author":"Cohen W.","year":"2003","unstructured":"W. Cohen , P. Ravikmar and and S. Fienberg. A Comparison of String Metrics for Matching Names and Records. Proc. of KDD Workshop on Data Cleaning , pp. 73 -- 78 , 2003 . W. Cohen, P. Ravikmar and and S. Fienberg. A Comparison of String Metrics for Matching Names and Records. Proc. of KDD Workshop on Data Cleaning, pp. 73--78, 2003."},{"key":"e_1_3_2_1_11_1","unstructured":"Flamingo Project http:\/\/www.ics.uci.edu\/flamingo\/.  Flamingo Project http:\/\/www.ics.uci.edu\/flamingo\/."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511574931","volume-title":"Algorithms on Strings, Trees and Sequences","author":"Gusfield D.","year":"1997","unstructured":"D. Gusfield . Algorithms on Strings, Trees and Sequences . Cambridge Univ. Press , 1997 . D. Gusfield. Algorithms on Strings, Trees and Sequences. Cambridge Univ. Press, 1997."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/303976.304001"},{"key":"e_1_3_2_1_14_1","first-page":"793","volume-title":"Proc. VLDB","author":"L. Jin","year":"2005","unstructured":"L. Jin et al. Indexing Mixed Types for Approximate Retrieval , Proc. VLDB , pp. 793 -- 804 , 2005 . L. Jin et al. Indexing Mixed Types for Approximate Retrieval, Proc. VLDB, pp. 793--804, 2005."},{"key":"e_1_3_2_1_15_1","first-page":"397","volume-title":"Proc. VLDB","author":"Jin L.","year":"2005","unstructured":"L. Jin and C. Li . Selectivity Estimation for Fuzzy String Predicates in Large Data Sets , Proc. VLDB , pp. 397 -- 408 , 2005 . L. Jin and C. Li. Selectivity Estimation for Fuzzy String Predicates in Large Data Sets, Proc. VLDB, pp. 397--408, 2005."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1316689.1316782"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233341"},{"key":"e_1_3_2_1_18_1","first-page":"195","volume-title":"Proc. VLDB","author":"Lee Hongrae","year":"2007","unstructured":"Hongrae Lee , Raymond T. Ng , and Kyuseok Shim , Extending Q-Grams to Estimate Selectivity of String Matching with Edit Distance , Proc. VLDB , pp. 195 -- 206 , 2007 . Hongrae Lee, Raymond T. Ng, and Kyuseok Shim, Extending Q-Grams to Estimate Selectivity of String Matching with Edit Distance, Proc. VLDB, pp. 195--206, 2007."},{"key":"e_1_3_2_1_19_1","first-page":"303","volume-title":"Xiaochun Yang. VGRAM: Improving Performance of Approximate Queries on String Collections Using VariableLength Grams Proc. VLDB","author":"Li Chen","year":"2007","unstructured":"Chen Li , Bin Wang , and Xiaochun Yang. VGRAM: Improving Performance of Approximate Queries on String Collections Using VariableLength Grams Proc. VLDB , pp. 303 -- 314 , 2007 . Chen Li, Bin Wang, and Xiaochun Yang. VGRAM: Improving Performance of Approximate Queries on String Collections Using VariableLength Grams Proc. VLDB, pp. 303--314, 2007."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872778"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/351827.384246"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775087"},{"key":"e_1_3_2_1_23_1","volume-title":"The State of Record Linkage and Current Research Problems. Statistics of Income Division","author":"W.","year":"1999","unstructured":"Winkler, W. E. The State of Record Linkage and Current Research Problems. Statistics of Income Division , U.S. Bureau of the Census, 1999 . Winkler, W. E. The State of Record Linkage and Current Research Problems. Statistics of Income Division, U.S. Bureau of the Census, 1999."}],"event":{"name":"EDBT\/ICDT '09: EDBT\/ICDT '09 joint conference","location":"Saint Petersburg Russia","acronym":"EDBT\/ICDT '09"},"container-title":["Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1516360.1516455","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1516360.1516455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:29:57Z","timestamp":1750253397000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1516360.1516455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3,24]]},"references-count":23,"alternative-id":["10.1145\/1516360.1516455","10.1145\/1516360"],"URL":"https:\/\/doi.org\/10.1145\/1516360.1516455","relation":{},"subject":[],"published":{"date-parts":[[2009,3,24]]},"assertion":[{"value":"2009-03-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}