{"id":"https://openalex.org/W2088600132","doi":"https://doi.org/10.1145/1102351.1102483","title":"2D Conditional Random Fields for Web information extraction","display_name":"2D Conditional Random Fields for Web information extraction","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2088600132","doi":"https://doi.org/10.1145/1102351.1102483","mag":"2088600132"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"},"type":"article","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/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770109","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-9795-4673"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100606995"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":23.7454,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99271477,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1044","last_page":"1051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"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/T11106","display_name":"Data Management and Algorithms","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/conditional-random-field","display_name":"Conditional random field","score":0.9595744609832764},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.9483718872070312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7874488830566406},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5773136019706726},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5149210691452026},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.503774106502533},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44831517338752747},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43145740032196045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3950824439525604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34395480155944824},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2487047016620636}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.9595744609832764},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9483718872070312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874488830566406},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5773136019706726},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5149210691452026},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.503774106502533},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44831517338752747},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43145740032196045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3950824439525604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34395480155944824},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2487047016620636},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1102351.1102483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1534730506","https://openalex.org/W1651266332","https://openalex.org/W1934019294","https://openalex.org/W1979960035","https://openalex.org/W1999595522","https://openalex.org/W2008652694","https://openalex.org/W2015551056","https://openalex.org/W2024581784","https://openalex.org/W2051434435","https://openalex.org/W2096071754","https://openalex.org/W2096175520","https://openalex.org/W2102667697","https://openalex.org/W2110896767","https://openalex.org/W2114220616","https://openalex.org/W2124189704","https://openalex.org/W2129712609","https://openalex.org/W2137813581","https://openalex.org/W2143309843","https://openalex.org/W2144087279","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2157316480","https://openalex.org/W2158823144","https://openalex.org/W2962735828","https://openalex.org/W2994982620"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W3108423214","https://openalex.org/W2011251309","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W2184553228","https://openalex.org/W1492005981"],"abstract_inverted_index":{"The":[0],"Web":[1,24,34,61,74],"contains":[2],"an":[3],"abundance":[4],"of":[5,28,43,120],"useful":[6],"semistructured":[7],"information":[8,25,58,75,95,112],"about":[9,26],"real":[10],"world":[11],"objects,":[12],"and":[13,114],"our":[14,121],"empirical":[15],"study":[16],"shows":[17],"that":[18],"strong":[19],"sequence":[20,49],"characteristics":[21,50],"exist":[22],"for":[23,73,110],"objects":[27],"the":[29,41,44,48,57,80,97,102,115,118],"same":[30],"type":[31],"across":[32],"different":[33],"sites.":[35],"Conditional":[36],"Random":[37],"Fields":[38],"(CRFs)":[39],"are":[40],"state":[42],"art":[45],"approaches":[46],"taking":[47],"to":[51,91],"do":[52],"better":[53,78],"labeling.":[54],"However,":[55],"as":[56],"on":[59],"a":[60,87],"page":[62],"is":[63],"two-dimensionally":[64],"laid":[65],"out,":[66],"previous":[67],"linear-chain":[68,107],"CRFs":[69],"have":[70],"their":[71],"limitations":[72],"extraction.":[76],"To":[77],"incorporate":[79],"two-dimensional":[81,88],"neighborhood":[82],"interactions,":[83],"this":[84],"paper":[85],"presents":[86],"CRF":[89,108],"model":[90,104],"automatically":[92],"extract":[93],"object":[94],"from":[96],"Web.":[98],"We":[99],"empirically":[100],"compare":[101],"proposed":[103],"with":[105],"existing":[106],"models":[109],"product":[111],"extraction,":[113],"results":[116],"show":[117],"effectiveness":[119],"model.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}