{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T11:44:03Z","timestamp":1725795843785},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319080093"},{"type":"electronic","value":"9783319080109"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-08010-9_20","type":"book-chapter","created":{"date-parts":[[2014,6,18]],"date-time":"2014-06-18T18:17:50Z","timestamp":1403115470000},"page":"180-191","source":"Crossref","is-referenced-by-count":1,"title":["Discovering Informative Contents of Web Pages"],"prefix":"10.1007","author":[{"given":"Qifeng","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunwei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lian\u2019en","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Rajagopalan, S.: Template detection via data mining and its applications. In: Proceedings of the 11th International Conference on World Wide Web, pp. 580\u2013591. ACM (2002)","DOI":"10.1145\/511446.511522"},{"key":"20_CR2","unstructured":"Cai, D., Yu, S., Wen, J.R., Ma, W.Y.: Vips: a visionbased page segmentation algorithm. Tech. rep., Microsoft technical report, MSR-TR-2003-79 (2003)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: Page-level template detection via isotonic smoothing. In: Proceedings of the 16th International Conference on World Wide Web, pp. 61\u201370. ACM (2007)","DOI":"10.1145\/1242572.1242582"},{"key":"20_CR4","unstructured":"Davison, B.D.: Recognizing nepotistic links on the web. In: Artificial Intelligence for Web Search, pp. 23\u201328 (2000)"},{"issue":"9","key":"20_CR5","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1109\/TKDE.2005.138","volume":"17","author":"S. Debnath","year":"2005","unstructured":"Debnath, S., Mitra, P., Pal, N., Giles, C.L.: Automatic identification of informative sections of web pages. IEEE Transactions on Knowledge and Data Engineerin\u00a017(9), 1233\u20131246 (2005)","journal-title":"IEEE Transactions on Knowledge and Data Engineerin"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Fernandes, D., de Moura, E.S., da Silva, A.S., Ribeiro-Neto, B., Braga, E.: A site oriented method for segmenting web pages. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 215\u2013224. ACM (2011)","DOI":"10.1145\/2009916.2009949"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Gibson, D., Punera, K., Tomkins, A.: The volume and evolution of web page templates. In: Special Interest Tracks and Posters of the 14th International Conference on World Wide Web, pp. 830\u2013839. ACM (2005)","DOI":"10.1145\/1062745.1062763"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Kao, H.Y., Chen, M.S., Lin, S.H., Ho, J.M.: Entropy-based link analysis for mining web informative structures. In: Proceedings of the Eleventh International Conference on Information and Knowledge Management, pp. 574\u2013581. ACM (2002)","DOI":"10.1145\/584883.584886"},{"issue":"5","key":"20_CR9","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/TKDE.2005.84","volume":"17","author":"H.Y. Kao","year":"2005","unstructured":"Kao, H.Y., Ho, J.M., Chen, M.S.: Wisdom: Web intrapage informative structure mining based on document object model. IEEE Transactions on Knowledge and Data Engineering\u00a017(5), 614\u2013627 (2005)","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Kushmerick, N.: Learning to remove internet advertisements. In: Proceedings of the Third Annual Conference on Autonomous Agents, pp. 175\u2013181. ACM (1999)","DOI":"10.1145\/301136.301186"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Lin, S.H., Ho, J.M.: Discovering informative content blocks from web documents. In: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 588\u2013593. ACM (2002)","DOI":"10.1145\/775047.775134"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Ma, L., Goharian, N., Chowdhury, A., Chung, M.: Extracting unstructured data from template generated web documents. In: Proceedings of the Twelfth International Conference on Information and Knowledge Management, pp. 512\u2013515. ACM (2003)","DOI":"10.1145\/956958.956961"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Reis, D.D.C., Golgher, P.B., Silva, A., Laender, A.: Automatic web news extraction using tree edit distance. In: Proceedings of the 13th International Conference on World Wide Web, pp. 502\u2013511. ACM (2004)","DOI":"10.1145\/988672.988740"},{"issue":"1","key":"20_CR14","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/584091.584093","volume":"5","author":"C.E. Shannon","year":"2001","unstructured":"Shannon, C.E.: A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review\u00a05(1), 3\u201355 (2001)","journal-title":"ACM SIGMOBILE Mobile Computing and Communications Review"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Song, R., Liu, H., Wen, J.R., Ma, W.Y.: Learning block importance models for web pages. In: Proceedings of the 13th International Conference on World Wide Web, pp. 203\u2013211. ACM (2004)","DOI":"10.1145\/988672.988700"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Vieira, K., da Silva, A.S., Pinto, N., de Moura, E.S., Cavalcanti, J., Freire, J.: A fast and robust method for web page template detection and removal. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pp. 258\u2013267. ACM (2006)","DOI":"10.1145\/1183614.1183654"},{"key":"20_CR17","unstructured":"Wang, J., Lochovsky, F.H.: Data-rich section extraction from html pages. In: Proceedings of the Third International Conference on Web Information Systems Engineering, WISE 2002, pp. 313\u2013322. IEEE (2002)"},{"key":"20_CR18","unstructured":"Yi, L., Liu, B.: Web page cleaning for web mining through feature weighting. In: International Joint Conference on Artificial Intelligence, vol.\u00a018, pp. 43\u201350. Lawrence Erlbaum Associates Ltd. (2003)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Yi, L., Liu, B., Li, X.: Eliminating noisy information in web pages for data mining. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 296\u2013305. ACM (2003)","DOI":"10.1145\/956755.956785"}],"container-title":["Lecture Notes in Computer Science","Web-Age Information Management"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-08010-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,26]],"date-time":"2019-05-26T23:13:37Z","timestamp":1558912417000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-08010-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319080093","9783319080109"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-08010-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}