{"id":"https://openalex.org/W2249470418","doi":"https://doi.org/10.1145/2736277.2741670","title":"Leveraging Pattern Semantics for Extracting Entities in Enterprises","display_name":"Leveraging Pattern Semantics for Extracting Entities in Enterprises","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2249470418","doi":"https://doi.org/10.1145/2736277.2741670","mag":"2249470418","pmid":"https://pubmed.ncbi.nlm.nih.gov/26705540"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043659320","display_name":"Fangbo Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fangbo Tao","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055778766","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-3799-9183"},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["LinkedIn, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"LinkedIn, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017633018","display_name":"Ariel Fuxman","orcid":"https://orcid.org/0009-0003-6760-997X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariel Fuxman","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421407","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-0403-7287"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["UC Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043659320"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.887,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91375381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2015","issue":null,"first_page":"1078","last_page":"1088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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":0.8320634365081787},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5825706124305725},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4974556267261505},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.48287490010261536},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48195597529411316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4633138179779053},{"id":"https://openalex.org/keywords/enterprise-information-system","display_name":"Enterprise information system","score":0.4371175467967987},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4172956049442291},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32684966921806335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2897433042526245},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2482733428478241},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13567021489143372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320634365081787},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5825706124305725},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4974556267261505},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.48287490010261536},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48195597529411316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4633138179779053},{"id":"https://openalex.org/C27295321","wikidata":"https://www.wikidata.org/wiki/Q831795","display_name":"Enterprise information system","level":2,"score":0.4371175467967987},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4172956049442291},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32684966921806335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2897433042526245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2482733428478241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13567021489143372},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2736277.2741670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmid:26705540","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26705540","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International World-Wide Web Conference. International WWW Conference","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4688019","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4688019","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4688019","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int World Wide Web Conf","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4688019","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W193898724","https://openalex.org/W197270748","https://openalex.org/W1489949474","https://openalex.org/W1509595041","https://openalex.org/W1512387364","https://openalex.org/W1554734378","https://openalex.org/W1565862766","https://openalex.org/W1766290689","https://openalex.org/W2022166150","https://openalex.org/W2068737686","https://openalex.org/W2094728533","https://openalex.org/W2101210369","https://openalex.org/W2103931177","https://openalex.org/W2104987630","https://openalex.org/W2115461474","https://openalex.org/W2117510361","https://openalex.org/W2121855012","https://openalex.org/W2124634352","https://openalex.org/W2128955272","https://openalex.org/W2129842875","https://openalex.org/W2132655161","https://openalex.org/W2133108446","https://openalex.org/W2167187514","https://openalex.org/W2201604718","https://openalex.org/W2251405440","https://openalex.org/W2471366537","https://openalex.org/W4285719527","https://openalex.org/W6633233822","https://openalex.org/W6678362882"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668","https://openalex.org/W2240384024"],"abstract_inverted_index":{"Entity":[0],"Extraction":[1],"is":[2,30,89],"a":[3,155],"process":[4],"of":[5,43,45,70,147,166,179,203],"identifying":[6],"meaningful":[7],"entities":[8,15,47,114,141],"from":[9,102],"text":[10],"documents.":[11],"In":[12],"enterprises,":[13,143],"extracting":[14,140],"improves":[16],"enterprise":[17,34,46,72,148,198],"efficiency":[18],"by":[19],"facilitating":[20],"numerous":[21],"applications,":[22],"including":[23],"search,":[24],"recommendation,":[25],"etc.":[26],"However,":[27],"the":[28,41,68,103,118,124,145,163,176,201],"problem":[29],"particularly":[31],"challenging":[32],"on":[33,109,117,196],"domains":[35],"due":[36],"to":[37,95,153,170,174],"several":[38],"reasons.":[39],"First,":[40],"lack":[42],"redundancy":[44],"makes":[48],"previous":[49],"web-based":[50],"systems":[51,65],"like":[52,63],"NELL":[53],"and":[54,150,188,192],"OpenIE":[55],"not":[56],"effective,":[57],"since":[58],"using":[59,75,185],"only":[60,125],"high-precision/low-recall":[61],"patterns":[62,78],"those":[64],"would":[66],"miss":[67],"majority":[69],"sparse":[71,80],"entities,":[73],"while":[74],"more":[76,190],"low-precision":[77],"in":[79,91,142],"setting":[81],"also":[82],"introduces":[83],"noise":[84],"drastically.":[85],"Second,":[86],"semantic":[87],"drift":[88],"common":[90],"enterprises":[92],"(\"Blue\"":[93],"refers":[94],"\"Windows":[96],"Blue\"),":[97],"such":[98],"that":[99],"public":[100,172],"signals":[101,122,173],"web":[104],"cannot":[105],"be":[106],"directly":[107],"applied":[108],"entities.":[110,194],"Moreover,":[111],"many":[112],"internal":[113,121],"never":[115],"appear":[116],"web.":[119],"Sparse":[120],"are":[123],"source":[126],"for":[127,139],"discovering":[128],"them.":[129],"To":[130],"address":[131],"these":[132],"challenges,":[133],"we":[134],"propose":[135],"an":[136],"end-to-end":[137],"framework":[138],"taking":[144],"input":[146],"corpus":[149],"limited":[151],"seeds":[152],"generate":[154],"high-quality":[156],"entity":[157],"collection":[158],"as":[159],"output.":[160],"We":[161],"introduce":[162],"novel":[164],"concept":[165],"Semantic":[167],"Pattern":[168],"Graph":[169],"leverage":[171],"understand":[175],"underlying":[177],"semantics":[178],"lexical":[180],"patterns,":[181],"reinforce":[182],"pattern":[183],"evaluation":[184],"mined":[186],"semantics,":[187],"yield":[189],"accurate":[191],"complete":[193],"Experiments":[195],"Microsoft":[197],"data":[199],"show":[200],"effectiveness":[202],"our":[204],"approach.":[205]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}