{"id":"https://openalex.org/W2067292826","doi":"https://doi.org/10.1145/2020408.2020574","title":"Entity disambiguation with hierarchical topic models","display_name":"Entity disambiguation with hierarchical topic models","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2067292826","doi":"https://doi.org/10.1145/2020408.2020574","mag":"2067292826"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020574","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh S. Kataria","raw_affiliation_strings":["Pennsylvania State University, State College, PA, USA","Pennsylvania State University, State College, PA., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University, State College, PA., USA#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054087481","display_name":"K. Sambath Kumar","orcid":"https://orcid.org/0000-0002-4962-9649"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishnan S. Kumar","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rajeev R. Rastogi","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105422045","display_name":"Prithviraj Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Prithviraj Sen","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038858575","display_name":"Srinivasan H. Sengamedu","orcid":"https://orcid.org/0000-0003-1847-8398"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Srinivasan H. Sengamedu","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1037","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8796590566635132},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7025469541549683},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6662063002586365},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6232001781463623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5736263990402222},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.536176323890686},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5212600827217102},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5209356546401978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5042315721511841},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4485524594783783},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4215678870677948},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.41452154517173767},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4105919599533081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22471553087234497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8796590566635132},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7025469541549683},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6662063002586365},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6232001781463623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5736263990402222},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.536176323890686},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5212600827217102},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5209356546401978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5042315721511841},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4485524594783783},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4215678870677948},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.41452154517173767},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4105919599533081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22471553087234497},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2020408.2020574","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.5702","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.5702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cis.fiu.edu/~lzhen001/activities/KDD2011Program/docs/p1037.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":31,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W190008395","https://openalex.org/W1536860849","https://openalex.org/W1548663377","https://openalex.org/W1880262756","https://openalex.org/W1969486090","https://openalex.org/W2001082470","https://openalex.org/W2094951132","https://openalex.org/W2096110600","https://openalex.org/W2098062695","https://openalex.org/W2098678088","https://openalex.org/W2100341149","https://openalex.org/W2106490775","https://openalex.org/W2110591510","https://openalex.org/W2115352105","https://openalex.org/W2122678284","https://openalex.org/W2122683976","https://openalex.org/W2131357087","https://openalex.org/W2137054688","https://openalex.org/W2139578439","https://openalex.org/W2153635508","https://openalex.org/W2158266063","https://openalex.org/W2167055514","https://openalex.org/W2171836785","https://openalex.org/W6607826182","https://openalex.org/W6639619044","https://openalex.org/W6674677251","https://openalex.org/W6674735981","https://openalex.org/W6674866097","https://openalex.org/W6676781583","https://openalex.org/W6683603713"],"related_works":["https://openalex.org/W2003899488","https://openalex.org/W4307536840","https://openalex.org/W4297775547","https://openalex.org/W2297176406","https://openalex.org/W3047601251","https://openalex.org/W3031970385","https://openalex.org/W2163194442","https://openalex.org/W4302211199","https://openalex.org/W2370554703","https://openalex.org/W3102628894"],"abstract_inverted_index":{"Disambiguating":[0],"entity":[1,49,100,114],"references":[2,101],"by":[3,164],"annotating":[4],"them":[5],"with":[6,153],"unique":[7],"ids":[8],"from":[9,52,145],"a":[10,13,41,63,94,139],"catalog":[11],"is":[12,62],"critical":[14],"step":[15],"in":[16,78,93,102,169],"the":[17,79,111],"enrichment":[18],"of":[19,44,113,171],"unstructured":[20],"content.":[21],"In":[22,150],"this":[23],"paper,":[24],"we":[25,157],"show":[26,158],"that":[27,73,89,159],"topic":[28],"models,":[29],"such":[30,56],"as":[31,57,165,167],"Latent":[32],"Dirichlet":[33],"Allocation":[34,70],"(LDA)":[35],"and":[36,125],"its":[37],"hierarchical":[38,65],"variants,":[39],"form":[40],"natural":[42],"class":[43],"models":[45,51],"for":[46,141],"learning":[47],"accurate":[48],"disambiguation":[50,172],"crowd-sourced":[53,147],"knowledge":[54],"bases":[55],"Wikipedia.":[58],"Our":[59],"main":[60],"contribution":[61],"semi-supervised":[64],"model":[66,123],"called":[67],"Wikipedia-based":[68],"Pachinko":[69],"Model}":[71],"(WPAM)":[72],"exploits:":[74],"(1)":[75],"All":[76],"words":[77,92,121],"Wikipedia":[80,103,106],"corpus":[81],"to":[82,108,116,130],"learn":[83],"word-entity":[84],"associations":[85],"(unlike":[86],"existing":[87],"approaches":[88],"only":[90],"use":[91],"small":[95],"fixed":[96],"window":[97],"around":[98],"annotated":[99,117],"pages),":[104],"(2)":[105],"annotations":[107],"appropriately":[109],"bias":[110],"assignment":[112],"labels":[115],"(and":[118],"co-occurring":[119],"unannotated)":[120],"during":[122],"learning,":[124],"(3)":[126],"Wikipedia's":[127,146],"category":[128,148],"hierarchy":[129],"capture":[131],"co-occurrence":[132],"patterns":[133],"among":[134],"entities.":[135],"We":[136],"also":[137],"propose":[138],"scheme":[140],"pruning":[142],"spurious":[143],"nodes":[144],"hierarchy.":[149],"our":[151],"experiments":[152],"multiple":[154],"real-life":[155],"datasets,":[156],"WPAM":[160],"outperforms":[161],"state-of-the-art":[162],"baselines":[163],"much":[166],"16%":[168],"terms":[170],"accuracy.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}