{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T21:04:18Z","timestamp":1761599058790,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2005,8,15]],"date-time":"2005-08-15T00:00:00Z","timestamp":1124064000000},"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":[[2005,8,15]]},"DOI":"10.1145\/1076034.1076079","type":"proceedings-article","created":{"date-parts":[[2005,11,7]],"date-time":"2005-11-07T17:34:39Z","timestamp":1131384879000},"page":"250-257","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["Title extraction from bodies of HTML documents and its application to web page retrieval"],"prefix":"10.1145","author":[{"given":"Yunhua","family":"Hu","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guomao","family":"Xin","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoping","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuming","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbo","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2005,8,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Eleventh Text REtrieval Conference (TREC-11)","author":"Amitay E.","year":"2002","unstructured":"Amitay , E. , Carmel , D. , Darlow , A. , Lempel , R. , and Soffer , A . Topic Distillation with Knowledge Agents , In Proceedings of the Eleventh Text REtrieval Conference (TREC-11) , 2002 .]] Amitay, E., Carmel, D., Darlow, A., Lempel, R., and Soffer, A.Topic Distillation with Knowledge Agents, In Proceedings of the Eleventh Text REtrieval Conference (TREC-11), 2002.]]"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the Second International Workshop on Web Document Analysis (WDA2003)","author":"Breuel T.M.","year":"2003","unstructured":"Breuel , T.M. Information Extraction from HTML Documents by Structural Matching , In Proceedings of the Second International Workshop on Web Document Analysis (WDA2003) , 2003 .]] Breuel, T.M. Information Extraction from HTML Documents by Structural Matching, In Proceedings of the Second International Workshop on Web Document Analysis (WDA2003), 2003.]]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/645327.649528"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Eleventh Text Retrieval Conference (TREC-11)","author":"Collins-Thompson K.","year":"2002","unstructured":"Collins-Thompson , K. , Ogilvie , P. , Zhang , Y. , and Callan , J . Information Filtering, Novelty Detection, and Named-Page Findiing , In Proceedings of the Eleventh Text Retrieval Conference (TREC-11) , 2002 .]] Collins-Thompson, K., Ogilvie, P., Zhang, Y., and Callan, J. Information Filtering, Novelty Detection, and Named-Page Findiing, In Proceedings of the Eleventh Text Retrieval Conference (TREC-11), 2002.]]"},{"key":"e_1_3_2_1_5_1","volume-title":"Overview of the TREC 2003 Web Track, In Proceedings of the Twelfth Text Retrieval Conference(TREC-2003)","author":"Craswell N.","year":"2003","unstructured":"Craswell , N. and Hawking , D . Overview of the TREC 2003 Web Track, In Proceedings of the Twelfth Text Retrieval Conference(TREC-2003) , 2003 .]] Craswell, N. and Hawking, D. Overview of the TREC 2003 Web Track, In Proceedings of the Twelfth Text Retrieval Conference(TREC-2003), 2003.]]"},{"key":"e_1_3_2_1_6_1","volume":"6","author":"Craven T.C. HTML","year":"2003","unstructured":"Craven , T.C. HTML Tags as Extraction Cues for Web Page Description Construction , Informing Science Journal , Volume 6 , 2003 .]] Craven, T.C. HTML Tags as Extraction Cues for Web Page Description Construction, Informing Science Journal, Volume 6, 2003.]]","journal-title":"Informing Science Journal"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Twenty-seventh International Conference on Very Large Databases(VLDB2001)","author":"Crescenzi V.","year":"2001","unstructured":"Crescenzi , V. , Mecca , G. and Merialdo , P . Roadrunner: Towards Automatic Data Extraction from Large Web Sites . In Proceedings of the Twenty-seventh International Conference on Very Large Databases(VLDB2001) , 2001 .]] Crescenzi, V., Mecca, G. and Merialdo, P. Roadrunner: Towards Automatic Data Extraction from Large Web Sites. In Proceedings of the Twenty-seventh International Conference on Very Large Databases(VLDB2001), 2001.]]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/508791.509009"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the USENIX Symposium on Internet Technologies and Systems (NISTS'97)","author":"Cutler M.","year":"1997","unstructured":"Cutler , M. , Shih , T. and Meng , Y . Using the Structure of HTML Documents to Improve Retrieval , In Proceedings of the USENIX Symposium on Internet Technologies and Systems (NISTS'97) , 1997 .]] Cutler, M., Shih, T. and Meng, Y. Using the Structure of HTML Documents to Improve Retrieval, In Proceedings of the USENIX Symposium on Internet Technologies and Systems (NISTS'97), 1997.]]"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of Human Language Technology Conference of the North American","author":"Evans D.K.","year":"2004","unstructured":"Evans , D.K. , Klavans , J.L. and McKeown , K.R. Columbia Newsblaster: Multilingual News Summarization on the Web . In Proceedings of Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics(HLT-NAACL-2004), 2004 .]] Evans, D.K., Klavans, J.L. and McKeown, K.R. Columbia Newsblaster: Multilingual News Summarization on the Web. In Proceedings of Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics(HLT-NAACL-2004), 2004.]]"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007601113994"},{"key":"e_1_3_2_1_13_1","volume-title":"A. Information Extraction with HMMs and Shrinkage. In Proceedings of the AAAI'99 Workshop on Machine Learning for Information Extraction (AAAI'99)","author":"Freitag D.","year":"1999","unstructured":"Freitag , D. and McCallum , A. Information Extraction with HMMs and Shrinkage. In Proceedings of the AAAI'99 Workshop on Machine Learning for Information Extraction (AAAI'99) , 1999 .]] Freitag, D. and McCallum, A. Information Extraction with HMMs and Shrinkage. In Proceedings of the AAAI'99 Workshop on Machine Learning for Information Extraction (AAAI'99), 1999.]]"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-2003)","author":"Kosala R.","year":"2003","unstructured":"Kosala , R. , Bruynooghe , M. , Bussche , J.V. and Blockeel , H . Information Extraction from Web Documents Based on Local Unranked Tree Automaton Inference , In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-2003) , 2003 .]] Kosala, R., Bruynooghe, M., Bussche, J.V. and Blockeel, H. Information Extraction from Web Documents Based on Local Unranked Tree Automaton Inference, In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-2003), 2003.]]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/645531.655993"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956826"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301191"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Twelfth Text Retrieval Conference (TREC-12)","author":"Ogilvie P.","year":"2003","unstructured":"Ogilvie , P. and Callan , J . Combining Structural Information and the Use of Priors in Mixed Named-Page and Homepage Finding , In Proceedings of the Twelfth Text Retrieval Conference (TREC-12) , 2003 .]] Ogilvie, P. and Callan, J. Combining Structural Information and the Use of Priors in Mixed Named-Page and Homepage Finding, In Proceedings of the Twelfth Text Retrieval Conference (TREC-12), 2003.]]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860463"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988740"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031171.1031181"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988700"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Thirteenth Text REtrieval Conference Proceedings (TREC-2004)","author":"Song R.","year":"2004","unstructured":"Song , R. , Wen , J.-R. , Shi , S. , Xin , G. , Liu , T.-Y. , Qin , T. , Zheng , X. , Zhang , J. , Xue , G. , and Ma , W . -Y. Microsoft Research Asia at Web Track and Terabyte Track of TREC 2004 . In Proceedings of the Thirteenth Text REtrieval Conference Proceedings (TREC-2004) , 2004 .]] Song, R., Wen, J.-R., Shi, S., Xin, G., Liu, T.-Y., Qin, T., Zheng, X., Zhang, J., Xue, G., and Ma, W.-Y. Microsoft Research Asia at Web Track and Terabyte Track of TREC 2004. In Proceedings of the Thirteenth Text REtrieval Conference Proceedings (TREC-2004), 2004.]]"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/986537.986630"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Eleventh Text REtrieval Conference (TREC-11)","author":"Zhang M.","year":"2002","unstructured":"Zhang , M. , Song , R. , Lin , C. , Ma , L. , Jiang , Z. , Jin , Y. , Liu , Y. , Zhao , L. and Ma , S . THU at TREC 2002: novelty, web, and filtering . In Proceedings of the Eleventh Text REtrieval Conference (TREC-11) , 2002 .]] Zhang, M., Song, R., Lin, C., Ma, L., Jiang, Z., Jin, Y., Liu, Y., Zhao, L. and Ma, S. THU at TREC 2002: novelty, web, and filtering. In Proceedings of the Eleventh Text REtrieval Conference (TREC-11), 2002.]]"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Twelfth International World Wide Web Conference (WWW2003)","author":"Zhang M.","year":"2003","unstructured":"Zhang , M. , Song , R. and Ma , S . DF or IDF? On the use of HTML primary feature fields for Web IR . In Proceedings of the Twelfth International World Wide Web Conference (WWW2003) , 2003 .]] Zhang, M., Song, R. and Ma, S. DF or IDF? On the use of HTML primary feature fields for Web IR. In Proceedings of the Twelfth International World Wide Web Conference (WWW2003), 2003.]]"}],"event":{"name":"SIGIR05: The 28th ACM\/SIGIR International Symposium on Information Retrieval 2005","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Salvador Brazil","acronym":"SIGIR05"},"container-title":["Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1076034.1076079","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1076034.1076079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:08:16Z","timestamp":1750262896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1076034.1076079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,8,15]]},"references-count":25,"alternative-id":["10.1145\/1076034.1076079","10.1145\/1076034"],"URL":"https:\/\/doi.org\/10.1145\/1076034.1076079","relation":{},"subject":[],"published":{"date-parts":[[2005,8,15]]},"assertion":[{"value":"2005-08-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}