{"id":"https://openalex.org/W2425146075","doi":"https://doi.org/10.1145/2882903.2912567","title":"Automatic Entity Recognition and Typing in Massive Text Data","display_name":"Automatic Entity Recognition and Typing in Massive Text Data","publication_year":2016,"publication_date":"2016-06-16","ids":{"openalex":"https://openalex.org/W2425146075","doi":"https://doi.org/10.1145/2882903.2912567","mag":"2425146075"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2912567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2912567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","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/A5009408707","display_name":"Xiang Ren","orcid":"https://orcid.org/0000-0001-8655-663X"},"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":"Xiang Ren","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/A5035119055","display_name":"Ahmed El-Kishky","orcid":"https://orcid.org/0000-0003-0121-7781"},"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":"Ahmed El-Kishky","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/A5103178893","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-7954-7994"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5009408707"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92686074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2235","last_page":"2239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8504770994186401},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5000050067901611},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4859117567539215},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4686676263809204},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4525716006755829},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4222824275493622},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.42047548294067383},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4005187749862671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3955431878566742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504770994186401},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5000050067901611},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4859117567539215},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4686676263809204},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4525716006755829},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4222824275493622},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.42047548294067383},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4005187749862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3955431878566742},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2912567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2912567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W638568100","https://openalex.org/W1934019294","https://openalex.org/W1964189668","https://openalex.org/W1982242209","https://openalex.org/W1996505782","https://openalex.org/W2004384146","https://openalex.org/W2004763266","https://openalex.org/W2015917093","https://openalex.org/W2016753842","https://openalex.org/W2020278455","https://openalex.org/W2024328138","https://openalex.org/W2024791376","https://openalex.org/W2037603696","https://openalex.org/W2046240631","https://openalex.org/W2048468185","https://openalex.org/W2075010670","https://openalex.org/W2092364718","https://openalex.org/W2094728533","https://openalex.org/W2096765155","https://openalex.org/W2096820050","https://openalex.org/W2103137496","https://openalex.org/W2111032703","https://openalex.org/W2111284344","https://openalex.org/W2111869785","https://openalex.org/W2112497803","https://openalex.org/W2114479635","https://openalex.org/W2115461474","https://openalex.org/W2119465010","https://openalex.org/W2132655161","https://openalex.org/W2134033474","https://openalex.org/W2134368421","https://openalex.org/W2138605095","https://openalex.org/W2144087279","https://openalex.org/W2145658888","https://openalex.org/W2148540243","https://openalex.org/W2150815390","https://openalex.org/W2153848201","https://openalex.org/W2158139315","https://openalex.org/W2167187514","https://openalex.org/W2172251087","https://openalex.org/W2223881431","https://openalex.org/W2236405165","https://openalex.org/W2251264718","https://openalex.org/W2251405440","https://openalex.org/W2295512975","https://openalex.org/W2406945108","https://openalex.org/W2807345617","https://openalex.org/W3104717349","https://openalex.org/W6713647626"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4377865234","https://openalex.org/W3005759282","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650","https://openalex.org/W2287770975"],"abstract_inverted_index":{"In":[0,58],"today's":[1],"computerized":[2],"and":[3,55,88,96,127,143,150,156,162,172],"information-based":[4],"society,":[5],"individuals":[6],"are":[7],"constantly":[8],"presented":[9],"with":[10],"vast":[11],"amounts":[12],"of":[13,28,42,46,53,69],"text":[14,74],"data,":[15,110],"ranging":[16],"from":[17,31,37],"news":[18,138],"articles,":[19,139],"scientific":[20],"publications,":[21],"product":[22,95],"reviews,":[23],"to":[24,49,65,122],"a":[25,99,123],"wide":[26],"range":[27],"textual":[29],"information":[30],"social":[32],"media.":[33],"To":[34],"extract":[35],"value":[36],"these":[38,103,165],"large,":[39],"multi-domain":[40],"pools":[41],"text,":[43],"it":[44],"is":[45],"great":[47],"importance":[48],"gain":[50],"an":[51],"understanding":[52],"entities":[54,68,167],"their":[56,90],"relationships.":[57],"this":[59],"tutorial,":[60],"we":[61],"introduce":[62],"data-driven":[63],"methods":[64,77,104],"recognize":[66],"typed":[67,166],"interest":[70],"in":[71,86,98,169],"massive,":[72],"domain-specific":[73],"corpora.":[75],"These":[76],"can":[78,118],"automatically":[79],"identify":[80],"token":[81],"spans":[82],"as":[83],"entity":[84],"mentions":[85],"documents":[87],"label":[89],"fine-grained":[91],"types":[92],"(e.g.,":[93,137,152],"people,":[94],"food)":[97],"scalable":[100],"way.":[101],"Since":[102],"do":[105],"not":[106],"rely":[107],"on":[108,131],"annotated":[109],"predefined":[111],"typing":[112],"schema":[113],"or":[114],"hand-crafted":[115],"features,":[116],"they":[117],"be":[119],"quickly":[120],"adapted":[121],"new":[124],"domain,":[125],"genre":[126],"language.":[128],"We":[129],"demonstrate":[130],"real":[132],"datasets":[133],"including":[134],"various":[135],"genres":[136],"discussion":[140],"forum":[141],"posts,":[142],"tweets),":[144],"domains":[145],"(general":[146],"vs.":[147],"bio-medical":[148],"domains)":[149],"languages":[151,159],"English,":[153],"Chinese,":[154],"Arabic,":[155],"even":[157],"low-resource":[158],"like":[160],"Hausa":[161],"Yoruba)":[163],"how":[164],"aid":[168],"knowledge":[170],"discovery":[171],"management.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}