{"id":"https://openalex.org/W2135769635","doi":"https://doi.org/10.1145/2600428.2609630","title":"Web page segmentation with structured prediction and its application in web page classification","display_name":"Web page segmentation with structured prediction and its application in web page classification","publication_year":2014,"publication_date":"2014-07-03","ids":{"openalex":"https://openalex.org/W2135769635","doi":"https://doi.org/10.1145/2600428.2609630","mag":"2135769635"},"language":"en","primary_location":{"id":"doi:10.1145/2600428.2609630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086674741","display_name":"Lidong Bing","orcid":"https://orcid.org/0000-0003-4565-6313"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lidong Bing","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101799598","display_name":"Rui Guo","orcid":"https://orcid.org/0000-0003-0659-4025"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Guo","raw_affiliation_strings":["Baidu Inc., Beijing, China","Baidu. Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu. Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Lam","orcid":"https://orcid.org/0000-0001-5479-377X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033269202","display_name":"Zheng-Yu Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Yu Niu","raw_affiliation_strings":["Baidu Inc., Beijing, China","Baidu. Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu. Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China","Baidu. Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu. Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0635,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.7761735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"767","last_page":"776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629767656326294},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6341457962989807},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5423752069473267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105694532394409},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.47553491592407227},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41763561964035034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.369229793548584},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20391538739204407},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0949261486530304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629767656326294},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6341457962989807},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5423752069473267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105694532394409},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.47553491592407227},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41763561964035034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.369229793548584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20391538739204407},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0949261486530304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2600428.2609630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W71104953","https://openalex.org/W1803802947","https://openalex.org/W1924133215","https://openalex.org/W1970841368","https://openalex.org/W1988937492","https://openalex.org/W1989338554","https://openalex.org/W2005311637","https://openalex.org/W2011506639","https://openalex.org/W2019264297","https://openalex.org/W2020254000","https://openalex.org/W2028904519","https://openalex.org/W2033403400","https://openalex.org/W2040075907","https://openalex.org/W2044958453","https://openalex.org/W2049020147","https://openalex.org/W2051097555","https://openalex.org/W2051141368","https://openalex.org/W2057510760","https://openalex.org/W2059586463","https://openalex.org/W2068842640","https://openalex.org/W2072489225","https://openalex.org/W2084358158","https://openalex.org/W2097645701","https://openalex.org/W2099111195","https://openalex.org/W2105842272","https://openalex.org/W2106985565","https://openalex.org/W2127847352","https://openalex.org/W2140208587","https://openalex.org/W2142385501","https://openalex.org/W2146486820","https://openalex.org/W2147428516","https://openalex.org/W2153635508","https://openalex.org/W2154484245","https://openalex.org/W2158051716","https://openalex.org/W2161861392","https://openalex.org/W2167859982","https://openalex.org/W2336259629","https://openalex.org/W2435251607","https://openalex.org/W3010318089","https://openalex.org/W4235169531","https://openalex.org/W4285719527","https://openalex.org/W6638151354","https://openalex.org/W6823566691"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W4379231730","https://openalex.org/W3135843367","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W4389858081","https://openalex.org/W4220741973","https://openalex.org/W2326464900","https://openalex.org/W4324315429","https://openalex.org/W1522196789"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,11,21,26,40,59,78,90],"framework":[3,107],"which":[4,84,115],"can":[5],"perform":[6],"Web":[7,28,137],"page":[8,29,41,138],"segmentation":[9,18,30,37,49,61,124],"with":[10],"structured":[12,22,94,102],"prediction":[13],"approach.":[14],"It":[15],"formulates":[16],"the":[17,35,43,47,55,63,69,73,86,101,112,120,133],"task":[19,66],"as":[20,89],"labeling":[23,52,71],"problem":[24],"on":[25,54,100],"transformed":[27,76],"graph":[31],"(WPS-graph).":[32],"WPS-graph":[33,56,74,88],"models":[34],"candidate":[36,123],"boundaries":[38],"of":[39,62,67,72,135],"and":[42],"dependency":[44],"relation":[45],"among":[46,122],"adjacent":[48],"boundaries.":[50,125],"Each":[51],"scheme":[53],"corresponds":[57],"to":[58,92,110,118],"possible":[60],"page.":[64],"The":[65],"finding":[68],"optimal":[70],"is":[75,108,116],"into":[77],"binary":[79],"Integer":[80],"Linear":[81],"Programming":[82],"problem,":[83],"considers":[85],"entire":[87],"whole":[91],"conduct":[93],"prediction.":[95],"A":[96],"learning":[97],"algorithm":[98],"based":[99],"output":[103],"Support":[104],"Vector":[105],"Machine":[106],"developed":[109],"determine":[111],"feature":[113],"weights,":[114],"capable":[117],"consider":[119],"inter-dependency":[121],"Furthermore,":[126],"we":[127],"investigate":[128],"its":[129],"efficacy":[130],"in":[131],"supporting":[132],"development":[134],"automatic":[136],"classification.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}