{"id":"https://openalex.org/W2157361576","doi":"https://doi.org/10.1145/1390334.1390367","title":"Enhancing text clustering by leveraging Wikipedia semantics","display_name":"Enhancing text clustering by leveraging Wikipedia semantics","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2157361576","doi":"https://doi.org/10.1145/1390334.1390367","mag":"2157361576"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","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/A5088890329","display_name":"Jian Hu","orcid":"https://orcid.org/0000-0003-0946-9617"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jian Hu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062920270","display_name":"Lujun Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lujun Fang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004299336","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-2891-4379"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":["Shanghai Jiao Tong Univeristy, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong Univeristy, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016928764","display_name":"Hua-Jun Zeng","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Hua-Jun Zeng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789012","display_name":"Hua Li","orcid":"https://orcid.org/0000-0002-6480-7386"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Hua Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science & Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science & Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665770","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0001-5252-4752"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":39.9672,"has_fulltext":false,"cited_by_count":197,"citation_normalized_percentile":{"value":0.99818316,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9959999918937683,"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":0.8379381895065308},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.8179830312728882},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6704590916633606},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6637091636657715},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.590754508972168},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.531532347202301},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5233108997344971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5182968974113464},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.46312767267227173},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4610172510147095},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.42492786049842834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42120397090911865},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4205414950847626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379381895065308},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.8179830312728882},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6704590916633606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6637091636657715},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.590754508972168},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.531532347202301},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5233108997344971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5182968974113464},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.46312767267227173},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4610172510147095},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.42492786049842834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42120397090911865},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4205414950847626},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1390334.1390367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.3198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.3198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/%7Eqyang/Docs/2008/fp422Hujian.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-21735","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-21735","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W89857650","https://openalex.org/W103965747","https://openalex.org/W130742730","https://openalex.org/W140312209","https://openalex.org/W158057341","https://openalex.org/W1493526108","https://openalex.org/W1498990157","https://openalex.org/W1548663377","https://openalex.org/W1573149547","https://openalex.org/W1578881253","https://openalex.org/W1604437383","https://openalex.org/W1651093245","https://openalex.org/W1979015808","https://openalex.org/W2005422315","https://openalex.org/W2069598966","https://openalex.org/W2071664212","https://openalex.org/W2081580037","https://openalex.org/W2098162425","https://openalex.org/W2100335205","https://openalex.org/W2115023510","https://openalex.org/W2118020653","https://openalex.org/W2120779048","https://openalex.org/W2123282528","https://openalex.org/W2138861205","https://openalex.org/W2149684865","https://openalex.org/W2949360895","https://openalex.org/W4243118217"],"related_works":["https://openalex.org/W2975283891","https://openalex.org/W780745626","https://openalex.org/W2251548944","https://openalex.org/W2997523947","https://openalex.org/W2043952800","https://openalex.org/W171586348","https://openalex.org/W3152877752","https://openalex.org/W2047143235","https://openalex.org/W2957377172","https://openalex.org/W2165693052"],"abstract_inverted_index":{"Most":[0,81],"traditional":[1,147],"text":[2,46,84,152],"clustering":[3,171,209],"methods":[4,40],"are":[5,99,196],"based":[6,13,119],"on":[7,14,28,120,157],"\"bag":[8],"of":[9,20,59,75,82,167,173,201],"words\"":[10],"(BOW)":[11],"representation":[12,47,85],"frequency":[15],"statistics":[16],"in":[17,51,143],"a":[18,73,112,116,135,202],"set":[19],"documents.":[21],"BOW,":[22],"however,":[23],"ignores":[24],"the":[25,29,52,83,121,165,170,186,199,208],"important":[26],"information":[27],"semantic":[30,122,141],"relationships":[31],"between":[32],"key":[33],"terms.":[34],"To":[35],"overcome":[36,106],"this":[37,103],"problem,":[38],"several":[39],"have":[41],"been":[42],"proposed":[43],"to":[44,105,114,138,145,180],"enrich":[45],"with":[48,94,164,185,198],"external":[49],"resource":[50],"past,":[53],"such":[54],"as":[55,178],"WordNet.":[56],"However,":[57],"many":[58],"these":[60,107,140],"approaches":[61],"suffer":[62],"from":[63,130],"some":[64],"limitations:":[65],"1)":[66],"WordNet":[67],"has":[68,72],"limited":[69],"coverage":[70],"and":[71,97,126,159,192],"lack":[74],"effective":[76],"word-sense":[77],"disambiguation":[78],"ability;":[79],"2)":[80],"enrichment":[86],"strategies,":[87],"which":[88],"append":[89],"or":[90],"replace":[91],"document":[92],"terms":[93],"their":[95],"hypernym":[96],"synonym,":[98,191],"overly":[100],"simple.":[101],"In":[102,183],"paper,":[104],"deficiencies,":[108],"we":[109,133],"first":[110],"propose":[111],"way":[113],"build":[115],"concept":[117],"thesaurus":[118],"relations":[123,142],"(synonym,":[124],"hypernym,":[125,190],"associative":[127,193],"relation)":[128],"extracted":[129],"Wikipedia.":[131],"Then,":[132],"develop":[134],"unified":[136],"framework":[137],"leverage":[139],"order":[144],"enhance":[146],"content":[148],"similarity":[149],"measure":[150],"for":[151,189],"clustering.":[153],"The":[154],"experimental":[155],"results":[156],"Reuters":[158],"OHSUMED":[160],"datasets":[161],"show":[162],"that":[163,195],"help":[166,200],"Wikipedia":[168],"thesaurus,":[169],"performance":[172,210],"our":[174],"method":[175],"is":[176],"improved":[177],"compared":[179],"previous":[181],"methods.":[182],"addition,":[184],"optimized":[187],"weights":[188],"concepts":[194],"tuned":[197],"few":[203],"labeled":[204],"data":[205],"users":[206],"provided,":[207],"can":[211],"be":[212],"further":[213],"improved.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":22}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}