{"id":"https://openalex.org/W1969300800","doi":"https://doi.org/10.1145/2396761.2396844","title":"Improving document clustering using automated machine translation","display_name":"Improving document clustering using automated machine translation","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W1969300800","doi":"https://doi.org/10.1145/2396761.2396844","mag":"1969300800"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2396844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","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/A5078061633","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0002-3208-2042"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["UC Davis, Davis, CA, USA","UC Davis, Davis, CA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"UC Davis, Davis, CA, USA,","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074506574","display_name":"Buyue Qian","orcid":"https://orcid.org/0000-0003-4780-5677"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buyue Qian","raw_affiliation_strings":["UC Davis, Davis, CA, USA","UC Davis, Davis, CA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"UC Davis, Davis, CA, USA,","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030289182","display_name":"Ian Davidson","orcid":"https://orcid.org/0000-0002-1258-4213"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Davidson","raw_affiliation_strings":["UC Davis, Davis, CA, USA","UC Davis, Davis, CA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"UC Davis, Davis, CA, USA,","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":2.347,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8925942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9990000128746033,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9990000128746033,"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":0.9954000115394592,"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":0.9879999756813049,"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":0.8320053815841675},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8314957022666931},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6461722254753113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4976790249347687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48347121477127075},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.4659479856491089},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.4526604413986206},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4510275423526764},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.447692334651947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4423035979270935},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.41160112619400024},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.34349292516708374},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2716062366962433},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0918334424495697},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0852837860584259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320053815841675},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8314957022666931},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6461722254753113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4976790249347687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48347121477127075},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4659479856491089},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.4526604413986206},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4510275423526764},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.447692334651947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4423035979270935},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.41160112619400024},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.34349292516708374},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2716062366962433},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0918334424495697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0852837860584259},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2396761.2396844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.643.1892","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.1892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucdavis.edu/~davidson/Publications/CIKM2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W19171709","https://openalex.org/W153995565","https://openalex.org/W1516407653","https://openalex.org/W1966918398","https://openalex.org/W1987756646","https://openalex.org/W1998450142","https://openalex.org/W2032175749","https://openalex.org/W2048679005","https://openalex.org/W2088857627","https://openalex.org/W2101324110","https://openalex.org/W2102650424","https://openalex.org/W2107667794","https://openalex.org/W2121947440","https://openalex.org/W2132914434","https://openalex.org/W2136294701","https://openalex.org/W2142742813","https://openalex.org/W2145765191","https://openalex.org/W2154415691","https://openalex.org/W2164535072","https://openalex.org/W2610857016","https://openalex.org/W4230094279","https://openalex.org/W4235169531","https://openalex.org/W6613554288","https://openalex.org/W6658528880","https://openalex.org/W6682991666","https://openalex.org/W6684067080"],"related_works":["https://openalex.org/W3146523624","https://openalex.org/W2951567704","https://openalex.org/W4300978037","https://openalex.org/W4312142847","https://openalex.org/W2969974905","https://openalex.org/W2535986621","https://openalex.org/W2186905933","https://openalex.org/W3011266291","https://openalex.org/W1525022337","https://openalex.org/W2160785859"],"abstract_inverted_index":{"With":[0],"the":[1,30,45,54,81,91,130,136,153,156],"development":[2],"of":[3,29,33,53,108,132],"statistical":[4],"machine":[5,95],"translation,":[6],"we":[7,43,71],"have":[8],"ready-to-use":[9],"tools":[10],"that":[11],"can":[12,42,127],"translate":[13],"documents":[14],"from":[15,94],"one":[16,114,117],"language":[17],"to":[18,38,48,65,76,104,123,143],"many":[19],"other":[20],"languages.":[21],"These":[22],"translations":[23],"provide":[24],"different":[25],"yet":[26,99],"correlated":[27],"views":[28],"same":[31],"set":[32],"documents.":[34],"This":[35],"gives":[36],"rise":[37],"an":[39,73],"intriguing":[40],"question:":[41],"use":[44],"extra":[46],"information":[47],"achieve":[49],"a":[50],"better":[51],"clustering":[52,61,83,131,146],"documents?":[55],"Some":[56],"recent":[57],"work":[58],"on":[59],"multiview":[60,145],"provided":[62],"positive":[63],"answers":[64],"this":[66,69,78,106],"question.":[67],"In":[68,141],"work,":[70],"propose":[72],"alternative":[74],"approach":[75],"address":[77],"problem":[79],"using":[80],"constrained":[82],"framework.":[84],"Unlike":[85],"traditional":[86],"Must-Link":[87],"and":[88,116,126],"Cannot-Link":[89],"constraints,":[90],"constraints":[92,109],"generated":[93],"translation":[96],"are":[97,121],"dense":[98],"noisy.":[100],"We":[101],"show":[102],"how":[103],"incorporate":[105],"type":[107],"by":[110],"presenting":[111],"two":[112],"algorithms,":[113,147],"parametric":[115],"non-parametric.":[118],"Our":[119],"algorithms":[120],"easy":[122],"implement,":[124],"efficient,":[125],"consistently":[128],"improve":[129],"real":[133],"data,":[134],"namely":[135],"Reuters":[137],"RCV1/RCV2":[138],"Multilingual":[139],"Dataset.":[140],"contrast":[142],"existing":[144],"our":[148],"technique":[149],"does":[150,161],"not":[151],"need":[152],"compatibility":[154],"or":[155],"conditional":[157],"independence":[158],"assumption,":[159],"nor":[160],"it":[162],"involve":[163],"subtle":[164],"parameter":[165],"tuning.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}