{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T09:31:29Z","timestamp":1791019889452,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,4,20]],"date-time":"2009-04-20T00:00:00Z","timestamp":1240185600000},"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":[[2009,4,20]]},"DOI":"10.1145\/1526709.1526840","type":"proceedings-article","created":{"date-parts":[[2009,4,21]],"date-time":"2009-04-21T10:17:17Z","timestamp":1240309037000},"page":"971-980","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["Extracting article text from the web with maximum subsequence segmentation"],"prefix":"10.1145","author":[{"given":"Jeff","family":"Pasternack","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Roth","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2009,4,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276330"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/365024.365102"},{"key":"e_1_3_2_1_3_1","volume-title":"Extracting content structure for web","author":"Cai D.","year":"2003","unstructured":"Cai , D. , Yu , S. , Wen , J.R. and Ma , W.Y . Extracting content structure for web pages based on visual representation. APWeb 2003 . Cai, D., Yu, S., Wen, J.R. and Ma, W.Y. Extracting content structure for web pages based on visual representation. APWeb 2003."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009068"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009070"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372161"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141277.1141534"},{"key":"e_1_3_2_1_9_1","volume-title":"VLDB","author":"Crescenzi V.","year":"2001","unstructured":"Crescenzi , V. , Mecca , G. and Merialdo , P . Roadrunner: Towards automatic data extraction from large web sites . VLDB 2001 . Crescenzi, V., Mecca, G. and Merialdo, P. Roadrunner: Towards automatic data extraction from large web sites. VLDB 2001."},{"key":"e_1_3_2_1_10_1","volume-title":"Experience With Top Gun Wingman: A Proxy-Based Graphical Web Browser for the 3Com PalmPilot. Middleware","author":"Fox A.","year":"1998","unstructured":"Fox , A. , Goldberg , I. , Gribble , S.D. , Lee , D.C. , Polito , A. and Brewer , E.A . Experience With Top Gun Wingman: A Proxy-Based Graphical Web Browser for the 3Com PalmPilot. Middleware 1998 . Fox, A., Goldberg, I., Gribble, S.D., Lee, D.C., Polito, A. and Brewer, E.A. Experience With Top Gun Wingman: A Proxy-Based Graphical Web Browser for the 3Com PalmPilot. Middleware 1998."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00100-9"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/565117.565137"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775134"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2000.839475"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/956863.956961"},{"key":"e_1_3_2_1_16_1","volume-title":"Web Page cleaning with Conditional Random Fields. WAC3","author":"Marek M.","year":"2007","unstructured":"Marek , M. , Pecina , P. , Spousta , M. Web Page cleaning with Conditional Random Fields. WAC3 2007 . Marek, M., Pecina, P., Spousta, M. Web Page cleaning with Conditional Random Fields. WAC3 2007."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1289189.1289212"},{"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":"10.1108\/eb046814"},{"key":"e_1_3_2_1_20_1","volume-title":"IJCAI","author":"Punyakanok V.","year":"2005","unstructured":"Punyakanok , V. , Roth , D. , Yih , W. and Zimak , D . Learning and inference over constrained output . IJCAI 2005 . Punyakanok, V., Roth, D., Yih, W. and Zimak, D. Learning and inference over constrained output. IJCAI 2005."},{"key":"e_1_3_2_1_21_1","volume-title":"ISMB","author":"Ruzzo W.L.","year":"1999","unstructured":"Ruzzo , W.L. and Tompa , M . A linear time algorithm for finding all maximal scoring subsequences . ISMB 1999 . Ruzzo, W.L. and Tompa, M. A linear time algorithm for finding all maximal scoring subsequences. ISMB 1999."},{"key":"e_1_3_2_1_22_1","unstructured":"Yi L. and Liu B. Web Page Cleaning for Web Mining through Feature Weighting. IJCAI-03.   Yi L. and Liu B. Web Page Cleaning for Web Mining through Feature Weighting. IJCAI-03."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956785"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775155"}],"event":{"name":"WWW '09: The 18th International World Wide Web Conference","location":"Madrid Spain","acronym":"WWW '09","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 18th international conference on World wide web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1526709.1526840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:29:47Z","timestamp":1750238987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,4,20]]},"references-count":23,"alternative-id":["10.1145\/1526709.1526840","10.1145\/1526709"],"URL":"https:\/\/doi.org\/10.1145\/1526709.1526840","relation":{},"subject":[],"published":{"date-parts":[[2009,4,20]]},"assertion":[{"value":"2009-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}