{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T09:07:09Z","timestamp":1725613629075},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642239816"},{"type":"electronic","value":"9783642239823"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23982-3_32","type":"book-chapter","created":{"date-parts":[[2011,9,24]],"date-time":"2011-09-24T05:47:44Z","timestamp":1316843264000},"page":"251-258","source":"Crossref","is-referenced-by-count":3,"title":["News Information Extraction Based on Adaptive Weighting Using Unsupervised Bayesian Algorithm"],"prefix":"10.1007","author":[{"given":"Shilin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deren","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"32_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/3-540-36901-5_42","volume-title":"Web Technologies and Applications","author":"D. Cai","year":"2003","unstructured":"Cai, D., Yu, S., Wen, J., Ma, W.-Y.: Extracting content structure for web pages based on visual representation. In: Zhou, X., Zhang, Y., Orlowska, M.E. (eds.) APWeb 2003. LNCS, vol.\u00a02642, pp. 406\u2013417. Springer, Heidelberg (2003)"},{"key":"32_CR2","unstructured":"Cai, D., Yu, S., Wen, J.-r., Ma W.-Y.: VIPS: a vision-based page segmentation algorithm. Technical Report MSR-TR-2003-79 (2003)"},{"key":"32_CR3","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1145\/1718487.1718501","volume-title":"Proceedings of the Third ACM International Conference on Web Search and Data Mining","author":"A. Carlson","year":"2010","unstructured":"Carlson, A., et al.: Coupled semi-supervised learning for information extraction. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, pp. 101\u2013110. ACM, New York (2010)"},{"key":"32_CR4","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1145\/1141277.1141534","volume-title":"Proceedings of the 2006 ACM Symposium on Applied Computing","author":"L. Chen","year":"2006","unstructured":"Chen, L., Ye, S., Li, X.: Template detection for large scale search engines. In: Proceedings of the 2006 ACM Symposium on Applied Computing, pp. 1094\u20131098. ACM, Dijon (2006)"},{"key":"32_CR5","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1145\/564691.564778","volume-title":"Proceedings of the 2002 ACM SIGMOD International Conference on Management of Data","author":"V. Crescenzi","year":"2002","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: RoadRunner: automatic data extraction from data-intensive web sites. In: Proceedings of the 2002 ACM SIGMOD International Conference on Management of Data, pp. 624\u2013624. ACM, Madison (2002)"},{"key":"32_CR6","unstructured":"Junfang, S., Li, L.: Web information extraction based on news domain ontology theory. In: IEEE 2nd Symposium on Web Society SWS (2010)"},{"issue":"1-2","key":"32_CR7","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/S0004-3702(99)00100-9","volume":"118","author":"N. Kushmerick","year":"2000","unstructured":"Kushmerick, N.: Wrapper induction: Efficiency and expressiveness. Artificial Intelligence\u00a0118(1-2), 15\u201368 (2000)","journal-title":"Artificial Intelligence"},{"key":"32_CR8","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-642-01891-6_5","volume-title":"Knowledge Discovery Enhanced with Semantic and Social Information","author":"M. Labsk\u00fd","year":"2009","unstructured":"Labsk\u00fd, M., Sv\u00e1tek, V., Nekvasil, M., Rak, D.: The ex project: Web information extraction using extraction ontologies. In: Berendt, B., Mladeni\u010d, D., de Gemmis, M., Semeraro, G., Spiliopoulou, M., Stumme, G., Sv\u00e1tek, V., \u017delezn\u00fd, F. (eds.) Knowledge Discovery Enhanced with Semantic and Social Information. Studies in Computational Intelligence, vol.\u00a0220, pp. 71\u201388. Springer, Heidelberg (2009)"},{"key":"32_CR9","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1145\/775047.775134","volume-title":"Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"S.-H. Lin","year":"2002","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, Edmonton (2002)"},{"key":"32_CR10","first-page":"601","volume-title":"Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"B. Liu","year":"2002","unstructured":"Liu, B., Grossman, R., Zhai, Y.: Mining data records in Web pages. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601\u2013606. ACM, Washington, D.C (2002)"},{"key":"32_CR11","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1145\/956863.956961","volume-title":"Proceedings of the Twelfth International Conference on Information and Knowledge Management","author":"L. Ma","year":"2003","unstructured":"Ma, L., et al.: Extracting unstructured data from template generated web documents. In: Proceedings of the Twelfth International Conference on Information and Knowledge Management, pp. 512\u2013515. ACM, New Orleans (2003)"},{"key":"32_CR12","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1145\/1526709.1526841","volume-title":"Proceedings of the 18th International Conference on World Wide Web","author":"G. Miao","year":"2009","unstructured":"Miao, G., et al.: Extracting data records from the web using tag path clustering. In: Proceedings of the 18th International Conference on World Wide Web, pp. 981\u2013990. ACM, Madrid (2009)"},{"key":"32_CR13","first-page":"155","volume":"4","author":"P.P. Michal Mared","year":"2007","unstructured":"Michal Mared, P.P., Spousta, M.: Web Page Cleaning with Conditional Random Fields. Calriers du Central\u00a04, 155\u2013162 (2007)","journal-title":"Calriers du Central"},{"issue":"1","key":"32_CR14","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1023\/A:1010022931168","volume":"4","author":"I. Muslea","year":"2001","unstructured":"Muslea, I., Minton, S., Knoblock, C.A.: Hierarchical Wrapper Induction for Semistructured Information Sources. Autonomous Agents and Multi-Agent Systems\u00a04(1), 93\u2013114 (2001)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1145\/1526709.1526840","volume-title":"Proceedings of the 18th International Conference on World Wide Web","author":"J. Pasternack","year":"2009","unstructured":"Pasternack, J., Roth, D.: Extracting article text from the web with maximum subsequence segmentation. In: Proceedings of the 18th International Conference on World Wide Web, pp. 971\u2013980. ACM, Madrid (2009)"},{"key":"32_CR16","unstructured":"Shoubiao, T., Jin, F., Yuan, J.: Web Data Extraction Based on Label Library. In: 2009 WRI World Congress on Computer Science and Information Engineering, (2009)"},{"key":"32_CR17","volume-title":"Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Z. Shuyi","year":"2007","unstructured":"Shuyi, Z., et al.: Joint optimization of wrapper generation and template detection. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, San Jose (2007)"},{"key":"32_CR18","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/1099554.1099672","volume-title":"Proceedings of the 14th ACM International Conference on Information and Knowledge Management","author":"K. Simon","year":"2005","unstructured":"Simon, K., Lausen, G.: ViPER: augmenting automatic information extraction with visual perceptions. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management, pp. 381\u2013388. ACM, Bremen (2005)"},{"issue":"1","key":"32_CR19","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1145\/1189740.1189746","volume":"7","author":"W. Tak-Lam","year":"2007","unstructured":"Tak-Lam, W., Wai, L.: Adapting Web information extraction knowledge via mining site-invariant and site-dependent features. ACM Trans. Internet Technol.\u00a07(1), 6 (2007)","journal-title":"ACM Trans. Internet Technol."},{"issue":"2","key":"32_CR20","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11280-007-0021-1","volume":"10","author":"S. Vadrevu","year":"2007","unstructured":"Vadrevu, S., Gelgi, F., Davulcu, H.: Information Extraction from Web Pages Using Presentation Regularities and Domain Knowledge. World Wide Web\u00a010(2), 157\u2013179 (2007)","journal-title":"World Wide Web"},{"key":"32_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1145\/1557019.1557163","volume-title":"Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"J. Wang","year":"2009","unstructured":"Wang, J., et al.: Can we learn a template-independent wrapper for news article extraction from a single training site? In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1345\u20131354. ACM, Paris (2009)"},{"key":"32_CR22","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1145\/1526709.1526868","volume-title":"Proceedings of the 18th International Conference on World Wide Web","author":"J. Wang","year":"2009","unstructured":"Wang, J., et al.: News article extraction with template-independent wrapper. In: Proceedings of the 18th International Conference on World Wide Web, pp. 1085\u20131086. ACM, Madrid (2009)"},{"issue":"1","key":"32_CR23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.datak.2008.08.009","volume":"68","author":"T.-L. Wong","year":"2009","unstructured":"Wong, T.-L., Lam, W.: An unsupervised method for joint information extraction and feature mining across different Web sites. Data & Knowledge Engineering\u00a068(1), 107\u2013125 (2009)","journal-title":"Data & Knowledge Engineering"},{"key":"32_CR24","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1145\/1571941.1571991","volume-title":"Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"T.-L. Wong","year":"2009","unstructured":"Wong, T.-L., Lam, W., Chen, B.: Mining employment market via text block detection and adaptive cross-domain information extraction. In: Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 283\u2013290. ACM, Boston (2009)"},{"key":"32_CR25","first-page":"147","volume":"45","author":"J.-P. Xiao","year":"2009","unstructured":"Xiao, J.-P., Zhang, L.-S., Ren, X.: Web information extraction based on Transductive Support Vector Machine. Jisuanji Gongcheng yu Yingyong (Computer Engineering and Applications)\u00a045, 147\u2013149 (2009)","journal-title":"Jisuanji Gongcheng yu Yingyong (Computer Engineering and Applications)"},{"issue":"2","key":"32_CR26","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11280-007-0022-0","volume":"10","author":"Y. Zhai","year":"2007","unstructured":"Zhai, Y., Liu, B.: Extracting Web Data Using Instance-Based Learning. World Wide Web\u00a010(2), 113\u2013132 (2007)","journal-title":"World Wide Web"},{"key":"32_CR27","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1145\/1060745.1060761","volume-title":"Proceedings of the 14th International Conference on World Wide Web","author":"Y. Zhai","year":"2005","unstructured":"Zhai, Y., Liu, B.: Web data extraction based on partial tree alignment. In: Proceedings of the 14th International Conference on World Wide Web, pp. 76\u201385. ACM, Chiba (2005)"},{"key":"32_CR28","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1145\/1281192.1281286","volume-title":"Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"H. Zhao","year":"2007","unstructured":"Zhao, H., Meng, W., Yu, C.: Mining templates from search result records of search engines. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 884\u2013893. ACM, San Jose (2007)"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems and Mining"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23982-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T07:14:34Z","timestamp":1638861274000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23982-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642239816","9783642239823"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23982-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}