{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:52:37Z","timestamp":1772567557010,"version":"3.50.1"},"reference-count":14,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2009,3,20]],"date-time":"2009-03-20T00:00:00Z","timestamp":1237507200000},"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":["SIGMOD Rec."],"published-print":{"date-parts":[[2009,3,20]]},"abstract":"<jats:p>In this paper we introduce the webpage understanding problem which consists of three subtasks: webpage segmentation, webpage structure labeling, and webpage text segmentation and labeling. The problem is motivated by the search applications we have been working on including Microsoft Academic Search, Windows Live Product Search and Renlifang Entity Relationship Search. We believe that integrated webpage understanding will be an important direction for future research in Web mining.<\/jats:p>","DOI":"10.1145\/1519103.1519111","type":"journal-article","created":{"date-parts":[[2009,4,6]],"date-time":"2009-04-06T16:34:22Z","timestamp":1239035662000},"page":"48-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Webpage understanding"],"prefix":"10.1145","volume":"37","author":[{"given":"Zaiqing","family":"Nie","sequence":"first","affiliation":[{"name":"Microsoft Research Asia, Beijing, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ying","family":"Ma","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2009,3,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009068"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009070"},{"key":"e_1_2_1_4_1","volume-title":"Carnegie Mellon University","author":"DiPasquo D.","year":"1998"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/844380.844764"},{"key":"e_1_2_1_6_1","volume-title":"Ji-Rong Wen and Wei-Ying Ma. Object-Level Vertical Search. Proc. of CIDR","author":"Nie Zaiqing","year":"2007"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242584"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060828"},{"key":"e_1_2_1_9_1","volume-title":"Proc. of NIPS","author":"Sarawagi S.","year":"2004"},{"key":"e_1_2_1_10_1","volume-title":"Proc. of SIGKDD","author":"Soderland S.","year":"1997"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988700"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458298"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281288"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150457"},{"key":"e_1_2_1_15_1","unstructured":"Jun Zhu Zaiqing Nie Bo Zhang and Ji-Rong Wen. Dynamic Hierarchical Markov Random Fields for Integrated Web Data Extraction. Journal of Machine Learning Research. 9(Jul): 1583--1614 2008.   Jun Zhu Zaiqing Nie Bo Zhang and Ji-Rong Wen. Dynamic Hierarchical Markov Random Fields for Integrated Web Data Extraction. Journal of Machine Learning Research. 9(Jul): 1583--1614 2008."}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1519103.1519111","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1519103.1519111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:29:53Z","timestamp":1750253393000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1519103.1519111"}},"subtitle":["beyond page-level search"],"short-title":[],"issued":{"date-parts":[[2009,3,20]]},"references-count":14,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2009,3,20]]}},"alternative-id":["10.1145\/1519103.1519111"],"URL":"https:\/\/doi.org\/10.1145\/1519103.1519111","relation":{},"ISSN":["0163-5808"],"issn-type":[{"value":"0163-5808","type":"print"}],"subject":[],"published":{"date-parts":[[2009,3,20]]},"assertion":[{"value":"2009-03-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}