{"id":"https://openalex.org/W2780385962","doi":"https://doi.org/10.1145/3148011.3154465","title":"WikiLDA","display_name":"WikiLDA","publication_year":2017,"publication_date":"2017-12-04","ids":{"openalex":"https://openalex.org/W2780385962","doi":"https://doi.org/10.1145/3148011.3154465","mag":"2780385962"},"language":"en","primary_location":{"id":"doi:10.1145/3148011.3154465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3154465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference","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/A5085277599","display_name":"Swapnil Hingmire","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Swapnil Hingmire","raw_affiliation_strings":["TCS Research"],"affiliations":[{"raw_affiliation_string":"TCS Research","institution_ids":["https://openalex.org/I4210104194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091240335","display_name":"Sutanu Chakraborti","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sutanu Chakraborti","raw_affiliation_strings":["IIT Madras"],"affiliations":[{"raw_affiliation_string":"IIT Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091609490","display_name":"Girish Keshav Palshikar","orcid":"https://orcid.org/0000-0003-3625-6705"},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Girish Palshikar","raw_affiliation_strings":["TCS Research"],"affiliations":[{"raw_affiliation_string":"TCS Research","institution_ids":["https://openalex.org/I4210104194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004265735","display_name":"Abhay Sodani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhay Sodani","raw_affiliation_strings":["TCS Research"],"affiliations":[{"raw_affiliation_string":"TCS Research","institution_ids":["https://openalex.org/I4210104194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085277599"],"corresponding_institution_ids":["https://openalex.org/I4210104194"],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72201133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"101","issue":null,"first_page":"1","last_page":"4"},"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":0.9995999932289124,"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":0.9965999722480774,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8102147579193115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8015247583389282},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.687089741230011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6549544334411621},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5924823880195618},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5736585855484009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564165115356445},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5089752674102783},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4823286235332489},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4665006995201111},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.45750901103019714},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.45259949564933777},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4480944275856018},{"id":"https://openalex.org/keywords/append","display_name":"Append","score":0.4457465410232544},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4349576532840729},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19720187783241272},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18009072542190552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10119345784187317}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8102147579193115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015247583389282},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.687089741230011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6549544334411621},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5924823880195618},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5736585855484009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564165115356445},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5089752674102783},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4823286235332489},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4665006995201111},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.45750901103019714},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.45259949564933777},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4480944275856018},{"id":"https://openalex.org/C2777998813","wikidata":"https://www.wikidata.org/wiki/Q16869124","display_name":"Append","level":2,"score":0.4457465410232544},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4349576532840729},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19720187783241272},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18009072542190552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10119345784187317},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3148011.3154465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3154465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1608334810","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2004770806","https://openalex.org/W2016196732","https://openalex.org/W2020386093","https://openalex.org/W2061320239","https://openalex.org/W2092970348","https://openalex.org/W2103587173","https://openalex.org/W2113499583","https://openalex.org/W2120779048","https://openalex.org/W2130339025","https://openalex.org/W2131070108","https://openalex.org/W2153222072","https://openalex.org/W2157522502","https://openalex.org/W2159426623","https://openalex.org/W2223881431","https://openalex.org/W2250533720","https://openalex.org/W2572434179","https://openalex.org/W4210764005"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Towards":[0],"the":[1,55,61,73,134],"goal":[2],"of":[3,6,58,109],"enhancing":[4],"interpretability":[5],"Latent":[7],"Dirichlet":[8],"Allocation":[9],"(LDA)":[10],"topics,":[11],"we":[12,31],"propose":[13],"WikiLDA,":[14,23],"an":[15],"enhancement":[16],"to":[17,46,77,122,138],"LDA":[18],"using":[19],"Wikipedia":[20,37],"concepts.":[21,38],"In":[22],"initially,":[24],"for":[25,91,100],"each":[26],"document":[27],"in":[28,85,113,125,131],"a":[29,107,114],"corpus":[30],"\"sprinkle\"":[32],"(append)":[33],"its":[34],"most":[35,62],"relevant":[36],"We":[39],"then":[40],"use":[41],"Generalized":[42],"P\u00f3lya":[43],"Urn":[44],"(GPU)":[45],"incorporate":[47],"word-word,":[48],"word-concept,":[49],"and":[50,81,117],"concept-concept":[51],"semantic":[52],"relatedness":[53],"into":[54],"generative":[56],"process":[57],"LDA.":[59],"As":[60],"probable":[63],"concepts":[64],"from":[65,89],"inferred":[66],"topics":[67,74],"can":[68],"be":[69],"referred":[70],"on":[71],"Wikipedia,":[72],"are":[75,136],"likely":[76],"become":[78],"more":[79,83],"interpretable":[80],"hence":[82],"usable":[84],"acquiring":[86],"domain":[87],"knowledge":[88],"humans":[90],"various":[92],"text":[93,101,126],"mining":[94],"tasks":[95],"(e.g.":[96],"eliciting":[97],"topic":[98,119],"labels":[99],"classification).":[102],"Empirical":[103],"results":[104],"show":[105],"that":[106],"projection":[108],"documents":[110],"by":[111],"WikiLDA":[112],"semantically":[115],"enriched":[116],"coherent":[118],"space":[120],"leads":[121],"improved":[123],"performance":[124],"classification":[127],"like":[128],"tasks,":[129],"especially":[130],"domains":[132],"where":[133],"classes":[135],"hard":[137],"separate.":[139]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-01-05T00:00:00"}