{"id":"https://openalex.org/W2154445423","doi":"https://doi.org/10.1145/1526709.1526735","title":"Incorporating site-level knowledge to extract structured data from web forums","display_name":"Incorporating site-level knowledge to extract structured data from web forums","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2154445423","doi":"https://doi.org/10.1145/1526709.1526735","mag":"2154445423"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","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/A5002360117","display_name":"Jiang-Ming Yang","orcid":null},"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":"Jiang-Ming Yang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272117","display_name":"Rui Cai","orcid":"https://orcid.org/0000-0002-6499-2091"},"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":"Rui Cai","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638214","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0001-8165-840X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Wang","raw_affiliation_strings":["CSSAR, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSAR, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","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":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Dept. Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433824","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-6926-0538"},"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":"Lei Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.8459,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.9938004,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11719","display_name":"Data Quality and Management","score":0.9919000267982483,"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"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9835000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990305423736572},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6863008737564087},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6229128241539001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5739307403564453},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5697474479675293},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5484777092933655},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5373256802558899},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4624166190624237},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.43741676211357117},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.423959881067276},{"id":"https://openalex.org/keywords/page-view","display_name":"Page view","score":0.41911107301712036},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.2844253480434418},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.27732598781585693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2094152271747589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18629273772239685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990305423736572},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6863008737564087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6229128241539001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5739307403564453},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5697474479675293},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5484777092933655},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5373256802558899},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4624166190624237},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.43741676211357117},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.423959881067276},{"id":"https://openalex.org/C103645729","wikidata":"https://www.wikidata.org/wiki/Q911187","display_name":"Page view","level":5,"score":0.41911107301712036},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.2844253480434418},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.27732598781585693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2094152271747589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18629273772239685},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1526709.1526735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.3903","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.3903","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/leizhang/Paper/WWW2009_JiangMing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W47392883","https://openalex.org/W1599188306","https://openalex.org/W1973483159","https://openalex.org/W1977970897","https://openalex.org/W2023094000","https://openalex.org/W2034797903","https://openalex.org/W2088600132","https://openalex.org/W2096496923","https://openalex.org/W2100779529","https://openalex.org/W2105803339","https://openalex.org/W2115770258","https://openalex.org/W2116216325","https://openalex.org/W2129712609","https://openalex.org/W2132613313","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2147880316","https://openalex.org/W2157316480","https://openalex.org/W2171472464","https://openalex.org/W3149154678","https://openalex.org/W6601926695","https://openalex.org/W6635684370"],"related_works":["https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2793744252","https://openalex.org/W1516746680","https://openalex.org/W2557094866","https://openalex.org/W2469016277"],"abstract_inverted_index":{"Web":[0],"forums":[1,158],"have":[2],"become":[3],"an":[4,98],"important":[5],"data":[6,15,47],"resource":[7],"for":[8],"many":[9],"web":[10,18,51],"applications,":[11],"but":[12],"extracting":[13],"structured":[14,46,67],"from":[16,49,80],"unstructured":[17],"forum":[19,52,82],"pages":[20,138,147],"is":[21,56,183,189],"still":[22],"a":[23,59,160],"challenging":[24],"task":[25],"due":[26],"to":[27,57,65,86,114,149],"both":[28,103,197],"complex":[29],"page":[30],"layout":[31],"designs":[32],"and":[33,77,105,108,139,142,166,199],"unrestricted":[34],"user":[35],"created":[36],"posts.":[37],"In":[38,84],"this":[39],"paper,":[40],"we":[41,101],"study":[42],"the":[43,95,129,144,150,168,171,181,194],"problem":[44],"of":[45,146,170],"extraction":[48,90,164],"various":[50,175],"sites.":[53],"Our":[54],"target":[55],"find":[58],"solution":[60],"as":[61,63,70,136],"general":[62],"possible":[64],"extract":[66],"data,":[68],"such":[69,135],"post":[71,73,75,78,140],"title,":[72],"author,":[74],"time,":[76],"content":[79],"any":[81],"site.":[83],"contrast":[85],"most":[87],"existing":[88],"information":[89,163],"methods,":[91],"which":[92],"only":[93,186],"leverage":[94],"knowledge":[96,107,126,188,196],"inside":[97],"individual":[99],"page,":[100],"incorporate":[102],"page-level":[104,187],"site-level":[106,195],"employ":[109],"Markov":[110],"logic":[111],"networks":[112],"(MLNs)":[113],"effectively":[115],"integrate":[116],"all":[117],"useful":[118],"evidence":[119],"by":[120],"learning":[121],"their":[122],"importance":[123],"automatically.":[124],"Site-level":[125],"includes":[127],"(1)":[128],"linkages":[130],"among":[131],"different":[132],"object":[133],"pages,":[134,141],"list":[137],"(2)":[143],"interrelationships":[145],"belonging":[148],"same":[151],"object.":[152],"The":[153],"experimental":[154],"results":[155],"on":[156,174],"20":[157],"show":[159,179],"very":[161],"encouraging":[162],"performance,":[165],"demonstrate":[167],"ability":[169],"proposed":[172],"approach":[173],"forums.":[176],"We":[177],"also":[178],"that":[180],"performance":[182],"limited":[184],"if":[185],"used,":[190],"while":[191],"when":[192],"incorporating":[193],"precision":[198],"recall":[200],"can":[201],"be":[202],"significantly":[203],"improved.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}