{"id":"https://openalex.org/W2032865178","doi":"https://doi.org/10.1109/jproc.2012.2191369","title":"Statistical Entity Extraction From the Web","display_name":"Statistical Entity Extraction From the Web","publication_year":2012,"publication_date":"2012-06-14","ids":{"openalex":"https://openalex.org/W2032865178","doi":"https://doi.org/10.1109/jproc.2012.2191369","mag":"2032865178"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2012.2191369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2012.2191369","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-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/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8794,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95880712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"100","issue":"9","first_page":"2675","last_page":"2687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9973999857902527,"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/T11106","display_name":"Data Management and Algorithms","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8337960243225098},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5843527317047119},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5768271684646606},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5709537863731384},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5254033207893372},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5137518644332886},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.5028078556060791},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4945027530193329},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4832618832588196},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.4556364119052887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337960243225098},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5843527317047119},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5768271684646606},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5709537863731384},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5254033207893372},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5137518644332886},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.5028078556060791},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4945027530193329},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4832618832588196},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.4556364119052887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jproc.2012.2191369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2012.2191369","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W157725869","https://openalex.org/W1483829860","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1534597797","https://openalex.org/W1803802947","https://openalex.org/W1973483159","https://openalex.org/W1977970897","https://openalex.org/W1983599491","https://openalex.org/W2005688170","https://openalex.org/W2012179495","https://openalex.org/W2034416661","https://openalex.org/W2088600132","https://openalex.org/W2102372499","https://openalex.org/W2103931177","https://openalex.org/W2110896767","https://openalex.org/W2111625757","https://openalex.org/W2115461474","https://openalex.org/W2119821739","https://openalex.org/W2121871415","https://openalex.org/W2126539437","https://openalex.org/W2127855221","https://openalex.org/W2127978399","https://openalex.org/W2129629757","https://openalex.org/W2130766266","https://openalex.org/W2134964692","https://openalex.org/W2135046866","https://openalex.org/W2135186040","https://openalex.org/W2137096228","https://openalex.org/W2140204390","https://openalex.org/W2147880316","https://openalex.org/W2148540243","https://openalex.org/W2157316480","https://openalex.org/W2157525865","https://openalex.org/W2158188757","https://openalex.org/W2165516035","https://openalex.org/W2167138081","https://openalex.org/W2167859982","https://openalex.org/W2185093343","https://openalex.org/W2397761198","https://openalex.org/W2563489878","https://openalex.org/W3005931293","https://openalex.org/W3093414588","https://openalex.org/W4239510810","https://openalex.org/W6606335252","https://openalex.org/W6629638141","https://openalex.org/W6631933293","https://openalex.org/W6678126744","https://openalex.org/W6678737427","https://openalex.org/W6679944369","https://openalex.org/W6680339939","https://openalex.org/W6682082992","https://openalex.org/W6683226453","https://openalex.org/W6684169581","https://openalex.org/W6687005723"],"related_works":["https://openalex.org/W4300659695","https://openalex.org/W2187012497","https://openalex.org/W4249203355","https://openalex.org/W2076997587","https://openalex.org/W4230517744","https://openalex.org/W2780890200","https://openalex.org/W2561758991","https://openalex.org/W2024646113","https://openalex.org/W2042825220","https://openalex.org/W1982103929"],"abstract_inverted_index":{"There":[0],"are":[1],"various":[2],"kinds":[3],"of":[4,26,48,52,66],"valuable":[5],"semantic":[6],"information":[7,21,32,89],"about":[8],"real-world":[9],"entities":[10],"embedded":[11],"in":[12],"webpages":[13],"and":[14,17,73,103],"databases.":[15],"Extracting":[16],"integrating":[18],"these":[19],"entity":[20,36,71,88],"from":[22,75],"the":[23,49,53],"Web":[24],"is":[25],"great":[27],"significance.":[28],"Comparing":[29],"to":[30,39,44],"traditional":[31],"extraction":[33,37,65],"problems,":[34],"web":[35,96],"needs":[38],"solve":[40],"several":[41],"new":[42],"challenges":[43],"fully":[45],"take":[46],"advantage":[47],"unique":[50],"characteristic":[51],"Web.":[54,76],"In":[55],"this":[56],"paper,":[57],"we":[58],"introduce":[59,80],"our":[60],"recent":[61],"work":[62],"on":[63],"statistical":[64],"structured":[67],"entities,":[68,70],"named":[69],"facts":[72],"relations":[74],"We":[77,91],"also":[78],"briefly":[79],"iKnoweb,":[81],"an":[82],"interactive":[83],"knowledge":[84],"mining":[85],"framework":[86],"for":[87],"integration.":[90],"will":[92],"use":[93],"two":[94],"novel":[95],"applications,":[97],"Microsoft":[98],"Academic":[99],"Search":[100],"(aka":[101],"Libra)":[102],"EntityCube,":[104],"as":[105],"working":[106],"examples.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}