{"id":"https://openalex.org/W2904911136","doi":"https://doi.org/10.1145/3276473","title":"Wikipedia-Based Relatedness Measurements for Multilingual Short Text Clustering","display_name":"Wikipedia-Based Relatedness Measurements for Multilingual Short Text Clustering","publication_year":2018,"publication_date":"2018-12-14","ids":{"openalex":"https://openalex.org/W2904911136","doi":"https://doi.org/10.1145/3276473","mag":"2904911136"},"language":"en","primary_location":{"id":"doi:10.1145/3276473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3276473","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5102829391","display_name":"Tatsuya Nakamura","orcid":"https://orcid.org/0000-0002-8005-4513"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Nakamura","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8005-4513","affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010966769","display_name":"Masumi Shirakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masumi Shirakawa","raw_affiliation_strings":["Hapicom Inc., Japan and Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hapicom Inc., Japan and Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012025870","display_name":"Takahiro Hara","orcid":"https://orcid.org/0000-0003-4807-3156"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Hara","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063345953","display_name":"Shojiro Nishio","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shojiro Nishio","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.5924,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68032268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9955999851226807,"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":0.9948999881744385,"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":0.8178948760032654},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7377726435661316},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6941066980361938},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6900002360343933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6069483160972595},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5787030458450317},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5141168236732483},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4824124574661255},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4694722890853882},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4483250677585602},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4391898810863495},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4237286150455475},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.42151135206222534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178948760032654},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7377726435661316},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6941066980361938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6900002360343933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069483160972595},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5787030458450317},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5141168236732483},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4824124574661255},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4694722890853882},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4483250677585602},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4391898810863495},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4237286150455475},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.42151135206222534},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3276473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3276473","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7167867790","display_name":"Development of Platform Systems for Sharing Human-Sensor Data Generated by Mobile Users","funder_award_id":"26240013","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7375822490","display_name":null,"funder_award_id":"JP26240013","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W50119190","https://openalex.org/W82620304","https://openalex.org/W142078059","https://openalex.org/W158057341","https://openalex.org/W165057458","https://openalex.org/W165283731","https://openalex.org/W804133461","https://openalex.org/W1491314197","https://openalex.org/W1491611863","https://openalex.org/W1516946508","https://openalex.org/W1534625513","https://openalex.org/W1552847225","https://openalex.org/W1569089799","https://openalex.org/W1960027552","https://openalex.org/W1964209958","https://openalex.org/W1970544520","https://openalex.org/W1971350260","https://openalex.org/W1973897992","https://openalex.org/W1985511512","https://openalex.org/W2003948532","https://openalex.org/W2013579020","https://openalex.org/W2020360881","https://openalex.org/W2028544407","https://openalex.org/W2038021268","https://openalex.org/W2038124402","https://openalex.org/W2038721957","https://openalex.org/W2055261195","https://openalex.org/W2061922307","https://openalex.org/W2088314245","https://openalex.org/W2095122172","https://openalex.org/W2097645701","https://openalex.org/W2100341149","https://openalex.org/W2100958137","https://openalex.org/W2101196063","https://openalex.org/W2102153514","https://openalex.org/W2108281845","https://openalex.org/W2120779048","https://openalex.org/W2123142779","https://openalex.org/W2127218421","https://openalex.org/W2127289991","https://openalex.org/W2131357087","https://openalex.org/W2131427731","https://openalex.org/W2136930489","https://openalex.org/W2145679919","https://openalex.org/W2153064622","https://openalex.org/W2157361576","https://openalex.org/W2251733640","https://openalex.org/W2262787892","https://openalex.org/W2337480916","https://openalex.org/W2404527150","https://openalex.org/W2407580753","https://openalex.org/W2525778437","https://openalex.org/W2576754561","https://openalex.org/W2757601816","https://openalex.org/W2767477068","https://openalex.org/W2950577311","https://openalex.org/W2962795068","https://openalex.org/W4285719527","https://openalex.org/W4299527668"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W2353339150","https://openalex.org/W1500125366","https://openalex.org/W2501166272","https://openalex.org/W2551770406","https://openalex.org/W2146812779","https://openalex.org/W2598939209","https://openalex.org/W2137763598","https://openalex.org/W1557970708","https://openalex.org/W2035932585"],"abstract_inverted_index":{"Throughout":[0],"the":[1,47,66,95,101,138,153,178,186,199,220],"world,":[2],"people":[3],"can":[4,33,115,163,172],"post":[5],"information":[6],"about":[7],"their":[8,12],"local":[9],"area":[10],"in":[11,53,157,185,216],"own":[13],"languages":[14,55,71,159],"using":[15,233],"social":[16],"networking":[17],"services.":[18],"Multilingual":[19],"short":[20,50,88,124,132,246],"text":[21,89,133,247],"clustering":[22,174,196,248],"is":[23,56],"an":[24,169],"important":[25],"task":[26],"to":[27,36,62,118,148,211,225,228],"organize":[28],"such":[29,39],"information,":[30],"and":[31,43,176],"it":[32],"be":[34,73,116,164],"applied":[35,117,227],"various":[37,54],"applications,":[38],"as":[40,134],"event":[41],"detection":[42],"summarization.":[44],"However,":[45],"measuring":[46],"relatedness":[48,83,121,154,213,242],"between":[49,155,214],"texts":[51,147,156,215,229],"written":[52],"a":[57,111,130,135,149,207,234],"challenging":[58],"problem.":[59],"In":[60,75],"addition":[61],"handling":[63],"multiple":[64],"languages,":[65],"semantic":[67,82,96,120,205],"gaps":[68],"among":[69,122],"all":[70],"must":[72],"considered.":[74],"this":[76],"article,":[77],"we":[78],"propose":[79,168],"two":[80],"Wikipedia-based":[81],"measurement":[84],"methods":[85,93,128,201,222,240],"for":[86,244],"multilingual":[87,131,193,245],"clustering.":[90],"The":[91,126,238],"proposed":[92,127,200,209,221,239],"solve":[94],"gap":[97],"problem":[98],"by":[99,181],"incorporating":[100],"inter-language":[102],"links":[103],"of":[104,137,141],"Wikipedia":[105,142],"into":[106,231],"Extended":[107],"Naive":[108],"Bayes":[109],"(ENB),":[110],"probabilistic":[112],"method":[113,210],"that":[114,171,198],"measure":[119,212],"monolingual":[123],"texts.":[125],"represent":[129],"vector":[136,151,188],"English":[139,232],"version":[140],"articles":[143],"(entities).":[144],"By":[145],"transferring":[146],"unified":[150,187],"space,":[152],"different":[158,217],"with":[160],"similar":[161],"meanings":[162],"increased.":[165],"We":[166],"also":[167],"approach":[170],"improve":[173],"performance":[175],"reduce":[177],"processing":[179],"time":[180],"eliminating":[182],"language-specific":[183],"entities":[184],"space.":[189],"Experimental":[190],"results":[191],"on":[192],"Twitter":[194],"message":[195],"revealed":[197],"outperformed":[202],"cross-lingual":[203],"explicit":[204],"analysis,":[206],"previously":[208],"languages.":[218],"Moreover,":[219],"were":[223],"comparable":[224],"ENB":[226],"translated":[230],"proprietary":[235],"translation":[236,252],"service.":[237],"enabled":[241],"measurements":[243],"without":[249],"requiring":[250],"machine":[251],"processes.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}