{"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":1750307614489,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2008,11,24]],"date-time":"2008-11-24T00:00:00Z","timestamp":1227484800000},"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":[[2008,11,24]]},"DOI":"10.1145\/1497308.1497418","type":"proceedings-article","created":{"date-parts":[[2009,9,28]],"date-time":"2009-09-28T17:33:43Z","timestamp":1254159223000},"page":"591-595","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Combining content extraction heuristics"],"prefix":"10.1145","author":[{"given":"Thomas","family":"Gottron","sequence":"first","affiliation":[{"name":"Johannes Gutenberg-Universit\u00e4t Mainz, Mainz, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2008,11,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511522"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066677.1067065"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/11425274_30"},{"key":"e_1_3_2_1_4_1","unstructured":"C. Fairon H. Naets A. Kilgarriff and G.-M. de Schryver editors. WAC3: Proceedings of the 3rd web as corpus workshop incorporating cleaneval. Presses universitaires de Louvain Sept. 2007.  C. Fairon H. Naets A. Kilgarriff and G.-M. de Schryver editors. WAC3: Proceedings of the 3rd web as corpus workshop incorporating cleaneval . Presses universitaires de Louvain Sept. 2007."},{"volume-title":"DELOS Workshop: Personalisation and Recommender Systems in Digital Libraries","year":"2001","author":"Finn A.","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062763"},{"key":"e_1_3_2_1_7_1","first-page":"123","volume-title":"ITA '07: Proceedings of the 2nd International Conference on Internet Technologies and Applications","author":"Gottron T.","year":"2007"},{"key":"e_1_3_2_1_8_1","first-page":"66","volume-title":"EuroIMSA '08: Proceedings of the IASTED Conference on Internet and Multimedia Systems and Applications 2008","author":"Gottron T.","year":"2008"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1793274.1793284"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.43"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1135777.1135922"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775182"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062895"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-004-4873-3"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/603867.603873"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/360825.360861"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2004.1264821"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775134"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1083356.1083384"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/544220.544228"},{"key":"e_1_3_2_1_21_1","first-page":"7","volume-title":"WDA 2001: Proceedings of the First International Workshop on Web Document Analysis","author":"Rahman A. F. R.","year":"2001"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988740"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28640-0_40"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.12"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956785"}],"event":{"name":"iiWAS08: 10th International Conference on Information Integration and Web-based Applications & Services","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Linz Austria","acronym":"iiWAS08"},"container-title":["Proceedings of the 10th International Conference on Information Integration and Web-based Applications &amp; Services"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1497308.1497418","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1497308.1497418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:45:43Z","timestamp":1750250743000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1497308.1497418"}},"subtitle":["the\n            <i>CombinE<\/i>\n            system"],"short-title":[],"issued":{"date-parts":[[2008,11,24]]},"references-count":25,"alternative-id":["10.1145\/1497308.1497418","10.1145\/1497308"],"URL":"https:\/\/doi.org\/10.1145\/1497308.1497418","relation":{},"subject":[],"published":{"date-parts":[[2008,11,24]]},"assertion":[{"value":"2008-11-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}