{"id":"https://openalex.org/W1973483159","doi":"https://doi.org/10.1145/1150402.1150457","title":"Simultaneous record detection and attribute labeling in web data extraction","display_name":"Simultaneous record detection and attribute labeling in web data extraction","publication_year":2006,"publication_date":"2006-08-20","ids":{"openalex":"https://openalex.org/W1973483159","doi":"https://doi.org/10.1145/1150402.1150457","mag":"1973483159"},"language":"en","primary_location":{"id":"doi:10.1145/1150402.1150457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","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/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Zhu","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/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"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":"Zaiqing Nie","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/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"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":"Ji-Rong Wen","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/A5100744420","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-0302-2550"},"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":"Bo Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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/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":"Wei-Ying Ma","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100606995"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":43.0322,"has_fulltext":false,"cited_by_count":170,"citation_normalized_percentile":{"value":0.99772079,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"494","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8480491638183594},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6811259984970093},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6277368068695068},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5980446934700012},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5674397349357605},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.47169995307922363},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.41208183765411377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34650373458862305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480491638183594},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6811259984970093},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6277368068695068},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5980446934700012},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5674397349357605},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47169995307922363},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.41208183765411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34650373458862305},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1150402.1150457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.9660","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.9660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/jrwen/jrwen_files/publications/KDD06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W111380827","https://openalex.org/W1513861746","https://openalex.org/W1524234997","https://openalex.org/W1565064763","https://openalex.org/W1592796124","https://openalex.org/W1616576116","https://openalex.org/W1636244751","https://openalex.org/W1732623802","https://openalex.org/W1774330103","https://openalex.org/W1989338554","https://openalex.org/W2048468185","https://openalex.org/W2051434435","https://openalex.org/W2088600132","https://openalex.org/W2095844239","https://openalex.org/W2096496923","https://openalex.org/W2102667697","https://openalex.org/W2104086170","https://openalex.org/W2104884878","https://openalex.org/W2115770258","https://openalex.org/W2128341918","https://openalex.org/W2128836931","https://openalex.org/W2128962821","https://openalex.org/W2129712609","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2147880316","https://openalex.org/W2150721933","https://openalex.org/W2157316480","https://openalex.org/W2158188757","https://openalex.org/W2158823144","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2167859982","https://openalex.org/W3005522790","https://openalex.org/W4233527139","https://openalex.org/W4285719527","https://openalex.org/W6600586173","https://openalex.org/W6630656317","https://openalex.org/W6729308270"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2111726165","https://openalex.org/W1982302668","https://openalex.org/W1492005981","https://openalex.org/W3015234152","https://openalex.org/W1968042686"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"shown":[3],"the":[4,67,77,80,135,147],"feasibility":[5],"and":[6,26,43,48,117,146,156],"promise":[7],"of":[8,69,82],"templateindependent":[9],"Web":[10,129],"data":[11,23,41,89,130],"extraction.":[12,131],"However,":[13],"existing":[14,139],"approaches":[15,141],"use":[16],"decoupled":[17,140],"strategies":[18],"\u2013":[19],"attempting":[20],"to":[21,53],"do":[22],"record":[24,62,154],"detection":[25,63,155],"attribute":[27,73,83,157],"labeling":[28,74,84],"in":[29,72,93,152],"two":[30,56],"separate":[31],"phases.":[32],"In":[33,59],"this":[34],"paper,":[35],"we":[36],"show":[37,149],"that":[38],"separately":[39],"extracting":[40],"records":[42,90],"attributes":[44],"is":[45,100],"highly":[46],"ineffective":[47],"propose":[49],"a":[50,94],"probabilistic":[51],"model":[52,99,137],"perform":[54],"these":[55],"tasks":[57],"simultaneously.":[58],"our":[60],"approach,":[61],"can":[64,85,107,119],"benefit":[65],"from":[66],"availability":[68],"semantics":[70],"required":[71],"and,":[75],"at":[76],"same":[78],"time,":[79],"accuracy":[81],"be":[86],"improved":[87],"when":[88],"are":[91,125],"labeled":[92],"collective":[95],"manner.":[96],"The":[97],"proposed":[98,136],"called":[101],"Hierarchical":[102],"Conditional":[103],"Random":[104],"Fields.":[105],"It":[106],"efficiently":[108],"integrate":[109],"all":[110],"useful":[111],"features":[112],"by":[113],"learning":[114],"their":[115],"importance,":[116],"it":[118],"also":[120],"incorporate":[121],"hierarchical":[122],"interactions":[123],"which":[124],"very":[126],"important":[127],"for":[128,142],"We":[132],"empirically":[133],"compare":[134],"with":[138],"product":[143],"information":[144],"extraction,":[145],"results":[148],"significant":[150],"improvements":[151],"both":[153],"labeling.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}