{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:20:58Z","timestamp":1750306858638,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T00:00:00Z","timestamp":1396828800000},"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":[[2014,4,7]]},"DOI":"10.1145\/2567948.2579708","type":"proceedings-article","created":{"date-parts":[[2016,2,5]],"date-time":"2016-02-05T19:44:31Z","timestamp":1454701471000},"page":"1279-1284","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["An analysis of duplicate on web extracted objects"],"prefix":"10.1145","author":[{"given":"Stefano","family":"Ortona","sequence":"first","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2014,4,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339602"},{"key":"e_1_3_2_1_2_1","volume-title":"Extraction and integration of partially overlapping web sources. PVLDB, 6(10)","author":"Bronzi M.","year":"2013","unstructured":"M. Bronzi , V. Crescenzi , P. Merialdo , and P. Papotti . Extraction and integration of partially overlapping web sources. PVLDB, 6(10) , 2013 . M. Bronzi, V. Crescenzi, P. Merialdo, and P. Papotti. Extraction and integration of partially overlapping web sources. PVLDB, 6(10), 2013."},{"issue":"13","key":"e_1_3_2_1_3_1","first-page":"1486","volume":"6","author":"Chen L.","year":"2013","unstructured":"L. Chen , S. Ortona , G. Orsi , and M. Benedikt . Aggregating semantic annotators. PVLDB , 6 ( 13 ): 1486 -- 1497 , 2013 . L. Chen, S. Ortona, G. Orsi, and M. Benedikt. Aggregating semantic annotators. PVLDB, 6(13):1486--1497, 2013.","journal-title":"Aggregating semantic annotators. PVLDB"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402020"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.127"},{"key":"e_1_3_2_1_6_1","first-page":"73","volume-title":"IIWeb","volume":"2003","author":"Cohen W. W.","year":"2003","unstructured":"W. W. Cohen , P. D. Ravikumar , S. E. Fienberg , A comparison of string distance metrics for name-matching tasks . In IIWeb , volume 2003 , pages 73 -- 78 , 2003 . W. W. Cohen, P. D. Ravikumar, S. E. Fienberg, et al. A comparison of string distance metrics for name-matching tasks. In IIWeb, volume 2003, pages 73--78, 2003."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488412"},{"key":"e_1_3_2_1_8_1","volume-title":"Automatic wrappers for large scale web extraction. PVLDB, 4(4)","author":"Dalvi N.","year":"2011","unstructured":"N. Dalvi , R. Kumar , and M. Soliman . Automatic wrappers for large scale web extraction. PVLDB, 4(4) , 2011 . N. Dalvi, R. Kumar, and M. Soliman. Automatic wrappers for large scale web extraction. PVLDB, 4(4), 2011."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.9"},{"key":"e_1_3_2_1_10_1","volume-title":"Sheffield Dept. of CS","author":"H. C.","year":"2011","unstructured":"H. C. et. al. Text Processing with GATE (Version 6). U . Sheffield Dept. of CS , 2011 . H. C. et. al. Text Processing with GATE (Version 6). U. Sheffield Dept. of CS, 2011."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989373"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187980.2188025"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/335191.336568"},{"key":"e_1_3_2_1_14_1","volume-title":"The llunatic data-cleaning framework. PVLDB, 6(9)","author":"Geerts F.","year":"2013","unstructured":"F. Geerts , G. Mecca , P. Papotti , and D. Santoro . The llunatic data-cleaning framework. PVLDB, 6(9) , 2013 . F. Geerts, G. Mecca, P. Papotti, and D. Santoro. The llunatic data-cleaning framework. PVLDB, 6(9), 2013."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2396839"},{"key":"e_1_3_2_1_16_1","volume-title":"Exploiting content redundancy for web information extraction. PVLDB, 3(1--2)","author":"Gulhane P.","year":"2010","unstructured":"P. Gulhane , R. Rastogi , S. H. Sengamedu , and A. Tengli . Exploiting content redundancy for web information extraction. PVLDB, 3(1--2) , 2010 . P. Gulhane, R. Rastogi, S. H. Sengamedu, and A. Tengli. Exploiting content redundancy for web information extraction. PVLDB, 3(1--2), 2010."},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Association, 84(406)","author":"Jaro M. A.","year":"1989","unstructured":"M. A. Jaro . Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Association, 84(406) , 1989 . M. A. Jaro. Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Association, 84(406), 1989."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020474"},{"key":"e_1_3_2_1_19_1","volume-title":"Dedoop: efficient deduplication with hadoop. PVLDB, 5(12):1878--1881","author":"Kolb L.","year":"2012","unstructured":"L. Kolb , A. Thor , and E. Rahm . Dedoop: efficient deduplication with hadoop. PVLDB, 5(12):1878--1881 , 2012 . L. Kolb, A. Thor, and E. Rahm. Dedoop: efficient deduplication with hadoop. PVLDB, 5(12):1878--1881, 2012."},{"key":"e_1_3_2_1_20_1","volume-title":"Evaluation of entity resolution approaches on real-world match problems. PVLDB, 3(1--2)","author":"K\u00f6pcke H.","year":"2010","unstructured":"H. K\u00f6pcke , A. Thor , and E. Rahm . Evaluation of entity resolution approaches on real-world match problems. PVLDB, 3(1--2) , 2010 . H. K\u00f6pcke, A. Thor, and E. Rahm. Evaluation of entity resolution approaches on real-world match problems. PVLDB, 3(1--2), 2010."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2247596.2247662"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/543613.543644"},{"key":"e_1_3_2_1_23_1","volume-title":"Linking temporal records. PVLDB, 4(11)","author":"Li P.","year":"2011","unstructured":"P. Li , X. L. Dong , A. Maurino , and D. Srivastava . Linking temporal records. PVLDB, 4(11) , 2011 . P. Li, X. L. Dong, A. Maurino, and D. Srivastava. Linking temporal records. PVLDB, 4(11), 2011."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4379(01)00041-2"},{"key":"e_1_3_2_1_25_1","volume-title":"Data cleaning: Problems and current approaches","author":"Rahm E.","year":"2000","unstructured":"E. Rahm and H. H. Do . Data cleaning: Problems and current approaches . IEEE Data Eng. Bull ., 23(4), 2000 . E. Rahm and H. H. Do. Data cleaning: Problems and current approaches. IEEE Data Eng. Bull., 23(4), 2000."},{"key":"e_1_3_2_1_26_1","volume-title":"VLDB","volume":"1","author":"Raman V.","year":"2001","unstructured":"V. Raman and J. M. Hellerstein . Potter's wheel: An interactive data cleaning system . In VLDB , volume 1 , 2001 . V. Raman and J. M. Hellerstein. Potter's wheel: An interactive data cleaning system. In VLDB, volume 1, 2001."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.90"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350263"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/2021017.2021020"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.119"}],"event":{"name":"WWW '14: 23rd International World Wide Web Conference","sponsor":["IW3C2 International World Wide Web Conference Committee","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Korea","acronym":"WWW '14"},"container-title":["Proceedings of the 23rd International Conference on World Wide Web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2567948.2579708","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2567948.2579708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:10:31Z","timestamp":1750234231000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2567948.2579708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,7]]},"references-count":30,"alternative-id":["10.1145\/2567948.2579708","10.1145\/2567948"],"URL":"https:\/\/doi.org\/10.1145\/2567948.2579708","relation":{},"subject":[],"published":{"date-parts":[[2014,4,7]]},"assertion":[{"value":"2014-04-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}