{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:08:54Z","timestamp":1765231734676,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,8,12]],"date-time":"2007-08-12T00:00:00Z","timestamp":1186876800000},"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":[[2007,8,12]]},"DOI":"10.1145\/1281192.1281288","type":"proceedings-article","created":{"date-parts":[[2007,12,7]],"date-time":"2007-12-07T19:19:41Z","timestamp":1197055181000},"page":"903-912","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Webpage understanding"],"prefix":"10.1145","author":[{"given":"Jun","family":"Zhu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiqing","family":"Nie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiao-Wuen","family":"Hon","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2007,8,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872799"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375682"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244304322972685"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372182"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014065"},{"key":"e_1_3_2_2_6_1","volume-title":"Proc. of VLDB","author":"Crescenzi V.","year":"2001","unstructured":"V. Crescenzi , G. Mecca and P. Merialdo . ROADRUNNER: Towards Automatic Data Extraction from Large Web Sites . Proc. of VLDB , 2001 . V. Crescenzi, G. Mecca and P. Merialdo. ROADRUNNER: Towards Automatic Data Extraction from Large Web Sites. Proc. of VLDB, 2001."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073157"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304223"},{"key":"e_1_3_2_2_9_1","volume-title":"Using HTML Formatting to Aid in Natural Language Processing on the World Wide Web. Senior Honors Thesis","author":"DiPasquo D.","year":"1998","unstructured":"D. DiPasquo . Using HTML Formatting to Aid in Natural Language Processing on the World Wide Web. Senior Honors Thesis , Carnegie Mellon University , 1998 . D. DiPasquo. Using HTML Formatting to Aid in Natural Language Processing on the World Wide Web. Senior Honors Thesis, Carnegie Mellon University, 1998."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.61"},{"key":"e_1_3_2_2_11_1","volume-title":"Proc. of AAAI","author":"Freitag D.","year":"1998","unstructured":"D. Freitag . Information Extraction from HTML: Application of a General Machine Learning Approach . Proc. of AAAI , 1998 . D. Freitag. Information Extraction from HTML: Application of a General Machine Learning Approach. Proc. of AAAI, 1998."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/1117794.1117817"},{"key":"e_1_3_2_2_13_1","first-page":"269","article-title":"Bayesian updating in causal probabilistic networks by local computation","volume":"4","author":"Jensen F. V.","year":"1990","unstructured":"F. V. Jensen , S. L. Lauritzen and K. G. Olesen . Bayesian updating in causal probabilistic networks by local computation . Computational Statistics Quarterly , 4 : 269 -- 282 , 1990 . F. V. Jensen, S. L. Lauritzen and K. G. Olesen. Bayesian updating in causal probabilistic networks by local computation. Computational Statistics Quarterly, 4:269--82, 1990.","journal-title":"Computational Statistics Quarterly"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00100-9"},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of ICML","author":"Lafferty J.","year":"2001","unstructured":"J. Lafferty , A. McCallum and F. Pereira . Conditional random fields: Probabilistic models for segmenting and labeling sequence data . Proc. of ICML , 2001 . J. Lafferty, A. McCallum and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proc. of ICML, 2001."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007584"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622420.1622425"},{"key":"e_1_3_2_2_18_1","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning C.","year":"1999","unstructured":"C. Manning and H. Schutze . Foundations of Statistical Natural Language Processing . The MIT Press Cambridge , MA , May , 1999 . C. Manning and H. Schutze. Foundations of Statistical Natural Language Processing. The MIT Press Cambridge, MA, May, 1999."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101153"},{"key":"e_1_3_2_2_20_1","volume-title":"Proc. of NIPS","author":"Sarawagi S.","year":"2004","unstructured":"S. Sarawagi and W. W. Cohen . Semi-Markov Conditional Random Fields for Information Extraction . Proc. of NIPS , 2004 . S. Sarawagi and W. W. Cohen. Semi-Markov Conditional Random Fields for Information Extraction. Proc. of NIPS, 2004."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143944"},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of SIGKDD","author":"Soderland S.","year":"1997","unstructured":"S. Soderland . Learning to Extract Text-based Information from the World Wide Web . Proc. of SIGKDD , 1997 . S. Soderland. Learning to Extract Text-based Information from the World Wide Web. Proc. of SIGKDD, 1997."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007562322031"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150492"},{"key":"e_1_3_2_2_25_1","volume-title":"Proc. of the 9th International Workshop on Parsing Technologies","author":"Yoshimasa T.","year":"2005","unstructured":"T. Yoshimasa and T. Jun'ichi . Chunk Parsing Revisited . Proc. of the 9th International Workshop on Parsing Technologies , 2005 . T. Yoshimasa and T. Jun'ichi. Chunk Parsing Revisited. Proc. of the 9th International Workshop on Parsing Technologies, 2005."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060761"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060760"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102483"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150457"}],"event":{"name":"KDD07: The 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"],"location":"San Jose California USA","acronym":"KDD07"},"container-title":["Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1281192.1281288","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1281192.1281288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T14:57:55Z","timestamp":1750258675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1281192.1281288"}},"subtitle":["an integrated approach"],"short-title":[],"issued":{"date-parts":[[2007,8,12]]},"references-count":29,"alternative-id":["10.1145\/1281192.1281288","10.1145\/1281192"],"URL":"https:\/\/doi.org\/10.1145\/1281192.1281288","relation":{},"subject":[],"published":{"date-parts":[[2007,8,12]]},"assertion":[{"value":"2007-08-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}