{"id":"https://openalex.org/W2040683545","doi":"https://doi.org/10.1177/0165551511404867","title":"Double-pass clustering technique for multilingual document collections","display_name":"Double-pass clustering technique for multilingual document collections","publication_year":2011,"publication_date":"2011-05-09","ids":{"openalex":"https://openalex.org/W2040683545","doi":"https://doi.org/10.1177/0165551511404867","mag":"2040683545"},"language":"en","primary_location":{"id":"doi:10.1177/0165551511404867","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551511404867","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5109156717","display_name":"Kazuaki Kishida","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuaki Kishida","raw_affiliation_strings":["Keio University, Japan,","(Keio University, Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University, Japan,","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"(Keio University, Japan)","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109156717"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":1.5597,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82766484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":"3","first_page":"304","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9976999759674072,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8278838396072388},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8270236253738403},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7854640483856201},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6512192487716675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5538371205329895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.52880859375},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48112884163856506},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4665607810020447},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4642053246498108},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4546932578086853},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.452324241399765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41446205973625183},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1431727409362793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12211009860038757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278838396072388},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8270236253738403},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7854640483856201},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6512192487716675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5538371205329895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.52880859375},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48112884163856506},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4665607810020447},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4642053246498108},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4546932578086853},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.452324241399765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41446205973625183},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1431727409362793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12211009860038757},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551511404867","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551511404867","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W78076044","https://openalex.org/W78284816","https://openalex.org/W117170265","https://openalex.org/W203472813","https://openalex.org/W210033121","https://openalex.org/W1529369248","https://openalex.org/W1544275340","https://openalex.org/W1549750060","https://openalex.org/W1594112393","https://openalex.org/W1601724338","https://openalex.org/W1654045153","https://openalex.org/W1981257123","https://openalex.org/W2016181719","https://openalex.org/W2022050849","https://openalex.org/W2026027976","https://openalex.org/W2032773168","https://openalex.org/W2035121712","https://openalex.org/W2061809273","https://openalex.org/W2064742743","https://openalex.org/W2088539083","https://openalex.org/W2090955184","https://openalex.org/W2092094655","https://openalex.org/W2102070017","https://openalex.org/W2148212498","https://openalex.org/W2150102617","https://openalex.org/W2162059093","https://openalex.org/W2405675882","https://openalex.org/W2610593052","https://openalex.org/W2726585279","https://openalex.org/W2799061466","https://openalex.org/W2918757710","https://openalex.org/W3021520429","https://openalex.org/W4237592971","https://openalex.org/W4251088421","https://openalex.org/W4300626901"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2091301346","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4284703357"],"abstract_inverted_index":{"It":[0],"is":[1,52,123],"often":[2],"necessary":[3],"to":[4,47,93,142],"categorize":[5],"automatically":[6],"multilingual":[7,34,44,64,90],"document":[8,45,65,91,122,145],"sets,":[9],"in":[10,14,60,117,133],"which":[11,134],"documents":[12,102],"written":[13],"a":[15,77,114,139],"variety":[16],"of":[17,88,96,164],"languages":[18],"are":[19,58,147],"included,":[20],"into":[21],"topically":[22],"homogeneous":[23],"subsets,":[24],"such":[25],"as":[26],"when":[27],"applying":[28,89,138],"an":[29],"automatic":[30],"summarization":[31],"system":[32],"for":[33],"news":[35,104],"articles.":[36],"However,":[37],"there":[38],"have":[39],"been":[40],"few":[41],"studies":[42],"on":[43,73,86],"clustering":[46,56,81,92,140],"date.":[48],"In":[49],"particular,":[50],"it":[51],"not":[53],"known":[54],"whether":[55],"techniques":[57,69,156],"effective":[59],"medium-":[61],"or":[62,79],"large-scale":[63],"sets.":[66],"For":[67],"scalability,":[68],"should":[70],"be":[71],"based":[72],"dictionary-based":[74],"translation":[75,131,154],"and":[76,100],"single-":[78],"double-pass":[80,111],"algorithm.":[82],"This":[83],"article":[84],"reports":[85],"experiments":[87],"medium-scale":[94],"sets":[95],"English,":[97],"French,":[98],"German":[99],"Italian":[101],"(Reuters":[103],"articles).":[105],"The":[106],"results":[107],"show":[108],"that":[109,120],"the":[110,118,126,129,162],"algorithm":[112,141],"has":[113,149],"positive":[115],"effect":[116],"case":[119],"each":[121,143],"translated.":[124],"On":[125],"other":[127],"hand,":[128],"cluster":[130],"strategy":[132],"clusters":[135],"obtained":[136],"by":[137],"language":[144],"set":[146],"translated":[148],"almost":[150],"no":[151],"effect.":[152],"Also,":[153],"disambiguation":[155],"can":[157],"improve,":[158],"but":[159],"only":[160],"slightly,":[161],"effectiveness":[163],"clustering.":[165]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-10-10T00:00:00"}