{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:33:34Z","timestamp":1750307614679,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2008,10,30]],"date-time":"2008-10-30T00:00:00Z","timestamp":1225324800000},"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":[[2008,10,30]]},"DOI":"10.1145\/1458502.1458505","type":"proceedings-article","created":{"date-parts":[[2008,11,11]],"date-time":"2008-11-11T12:59:40Z","timestamp":1226408380000},"page":"9-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Automatic wrapper induction from hidden-web sources with domain knowledge"],"prefix":"10.1145","author":[{"given":"Pierre","family":"Senellart","sequence":"first","affiliation":[{"name":"INRIA Saclay & TELECOM ParisTech, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avin","family":"Mittal","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bombay, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Muschick","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Graz, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R\u00e9mi","family":"Gilleron","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Lille 3 & INRIA Lille, Villeneuve d'Ascq, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Tommasi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Lille 3 & INRIA Lille, Villeneuve d'Ascq, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2008,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. Simp\u00f3sio Brasileiro de Bancos de Dados","author":"Barbosa L.","year":"2004","unstructured":"L. Barbosa and J. Freire . Siphoning hidden-Web data through keyword-based interfaces . In Proc. Simp\u00f3sio Brasileiro de Bancos de Dados , Bras\u00edlia, Brasil , Oct. 2004 . L. Barbosa and J. Freire. Siphoning hidden-Web data through keyword-based interfaces. In Proc. Simp\u00f3sio Brasileiro de Bancos de Dados, Bras\u00edlia, Brasil, Oct. 2004."},{"volume-title":"White Paper","year":"2001","key":"e_1_3_2_1_2_1","unstructured":"BrightPlanet. The deep Web: Surfacing hidden value . White Paper , July 2001 . BrightPlanet. The deep Web: Surfacing hidden value. White Paper, July 2001."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9613-8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/977401.978166"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. VLDB","author":"Chuang S.-L.","year":"2007","unstructured":"S.-L. Chuang , K. C.-C. Chang , and C. Zhai . Context-aware wrapping: Synchronized data extraction . In Proc. VLDB , Vienna, Austria , Sept. 2007 . S.-L. Chuang, K. C.-C. Chang, and C. Zhai. Context-aware wrapping: Synchronized data extraction. In Proc. VLDB, Vienna, Austria, Sept. 2007."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. VLDB","author":"Crescenzi V.","year":"2001","unstructured":"V. Crescenzi , G. Mecca , and P. Merialdo . Roadrunner: Towards automatic data extraction from large Web sites . In Proc. VLDB , Roma, Italy , Sept. 2001 . V. Crescenzi, G. Mecca, and P. Merialdo. Roadrunner: Towards automatic data extraction from large Web sites. In Proc. VLDB, Roma, Italy, Sept. 2001."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267666"},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. AAAI","author":"Freitag D.","year":"2000","unstructured":"D. Freitag and N. Kushmerick . Boosted wrapper induction . In Proc. AAAI , Austin, USA , July 2000 . D. Freitag and N. Kushmerick. Boosted wrapper induction. In Proc. AAAI, Austin, USA, July 2000."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1018432.1021517"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1230819.1241670"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. VLDB","author":"Ipeirotis P. G.","year":"2002","unstructured":"P. G. Ipeirotis and L. Gravano . Distributed search over the hidden Web: Hierarchical database sampling and selection . In Proc. VLDB , Hong Kong, China , Aug. 2002 . P. G. Ipeirotis and L. Gravano. Distributed search over the hidden Web: Hierarchical database sampling and selection. In Proc. VLDB, Hong Kong, China, Aug. 2002."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. ECML Workshop on Mining and Learning in Graphs","author":"Jousse F.","year":"2006","unstructured":"F. Jousse , R. Gilleron , I. Tellier , and M. Tommasi . Conditional Random Fields for XML trees . In Proc. ECML Workshop on Mining and Learning in Graphs , Berlin, Germany , Sept. 2006 . F. Jousse, R. Gilleron, I. Tellier, and M. Tommasi. Conditional Random Fields for XML trees. In Proc. ECML Workshop on Mining and Learning in Graphs, Berlin, Germany, Sept. 2006."},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. ICML","author":"Lafferty J.","year":"2001","unstructured":"J. Lafferty , A. McCallum , and F. Pereira . Conditional Random Fields: Probabilistic models for segmenting and labeling sequence data . In Proc. ICML , Williamstown, USA , June 2001 . J. Lafferty, A. McCallum, and F. Pereira. Conditional Random Fields: Probabilistic models for segmenting and labeling sequence data. In Proc. ICML, Williamstown, USA, June 2001."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.83"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119206"},{"key":"e_1_3_2_1_16_1","volume-title":"Probing the hidden Web. Research internship report","author":"Mittal A.","year":"2007","unstructured":"A. Mittal . Probing the hidden Web. Research internship report . Technical Report 479, Gemo , INRIA Futurs , July 2007 . A. Mittal. Probing the hidden Web. Research internship report. Technical Report 479, Gemo, INRIA Futurs, July 2007."},{"key":"e_1_3_2_1_17_1","volume-title":"Universit\u00e9 de Technologie de Lille and Technischen Universit\u00e4t Graz","author":"Muschick D.","year":"2007","unstructured":"D. Muschick . Unsupervised learning of XML tree annotations. Master's thesis , Universit\u00e9 de Technologie de Lille and Technischen Universit\u00e4t Graz , June 2007 . D. Muschick. Unsupervised learning of XML tree annotations. Master's thesis, Universit\u00e9 de Technologie de Lille and Technischen Universit\u00e4t Graz, June 2007."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010022931168"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860479"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"e_1_3_2_1_21_1","unstructured":"Princeton University Cognitive Science Laboratory. WordNet. http:\/\/wordnet.princeton.edu\/.  Princeton University Cognitive Science Laboratory. WordNet. http:\/\/wordnet.princeton.edu\/."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. VLDB","author":"Raghavan S.","year":"2001","unstructured":"S. Raghavan and H. Garcia-Molina . Crawling the hidden Web . In Proc. VLDB , Roma, Italy , Sept. 2001 . S. Raghavan and H. Garcia-Molina. Crawling the hidden Web. In Proc. VLDB, Roma, Italy, Sept. 2001."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. NIPS","author":"Sarawagi S.","year":"2004","unstructured":"S. Sarawagi and W. W. Cohen . Semi-Markov conditional random fields for information extraction . In Proc. NIPS , Vancouver, Canada , Dec. 2004 . S. Sarawagi and W. W. Cohen. Semi-Markov conditional random fields for information extraction. In Proc. NIPS, Vancouver, Canada, Dec. 2004."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073473"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1596276.1596302"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39804-2_39"},{"key":"e_1_3_2_1_28_1","unstructured":"W3C. HTML 4.01 specification Sept. 1999. http:\/\/www.w3.org\/TR\/REC-html40\/.  W3C. HTML 4.01 specification Sept. 1999. http:\/\/www.w3.org\/TR\/REC-html40\/."},{"key":"e_1_3_2_1_29_1","unstructured":"W3C. Web Services Description Language (WSDL) 1.1 Mar. 2001. http:\/\/www.w3.org\/TR\/wsdl.  W3C. Web Services Description Language (WSDL) 1.1 Mar. 2001. http:\/\/www.w3.org\/TR\/wsdl."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/11607380_2"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060761"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007583"},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. VLDB","author":"Zhang Z.","year":"2005","unstructured":"Z. Zhang , B. He , and K. C.-C. Chang . Light-weight domain-based form assistant: Querying Web databases on the fly . In Proc. VLDB , Trondheim, Norway , Sept. 2005 . Z. Zhang, B. He, and K. C.-C. Chang. Light-weight domain-based form assistant: Querying Web databases on the fly. In Proc. VLDB, Trondheim, Norway, Sept. 2005."}],"event":{"name":"CIKM08: Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","ACM Association for Computing Machinery","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Napa Valley California USA","acronym":"CIKM08"},"container-title":["Proceedings of the 10th ACM workshop on Web information and data management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1458502.1458505","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1458502.1458505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:45:44Z","timestamp":1750250744000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1458502.1458505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,10,30]]},"references-count":32,"alternative-id":["10.1145\/1458502.1458505","10.1145\/1458502"],"URL":"https:\/\/doi.org\/10.1145\/1458502.1458505","relation":{},"subject":[],"published":{"date-parts":[[2008,10,30]]},"assertion":[{"value":"2008-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}