{"id":"https://openalex.org/W2888875874","doi":"https://doi.org/10.1002/pra2.2017.14505401056","title":"Document representation and clustering models for bilingual documents clustering","display_name":"Document representation and clustering models for bilingual documents clustering","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2888875874","doi":"https://doi.org/10.1002/pra2.2017.14505401056","mag":"2888875874"},"language":"en","primary_location":{"id":"doi:10.1002/pra2.2017.14505401056","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pra2.2017.14505401056","pdf_url":null,"source":{"id":"https://openalex.org/S4393918545","display_name":"Proceedings of the Association for Information Science and Technology","issn_l":"2373-9231","issn":["2373-9231"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Association for Information Science and Technology","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/A5053659741","display_name":"Shutian Ma","orcid":"https://orcid.org/0000-0002-8339-6412"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shutian Ma","raw_affiliation_strings":["Department of Information Management Nanjing University of Science and Technology  China","Department of Information Management, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Management Nanjing University of Science and Technology  China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Department of Information Management, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056318061","display_name":"Chengzhi Zhang","orcid":"https://orcid.org/0000-0001-9522-2914"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengzhi Zhang","raw_affiliation_strings":["Department of Information Management Nanjing University of Science and Technology  China","Department of Information Management, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Management Nanjing University of Science and Technology  China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Department of Information Management, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053659741","https://openalex.org/A5056318061"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.25511771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"54","issue":"1","first_page":"499","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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":0.998199999332428,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9952999949455261,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9916999936103821,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8805458545684814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.785132646560669},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7105202674865723},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.6043311953544617},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.601753294467926},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5909205079078674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5027186870574951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48799413442611694},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.46851515769958496},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.44878721237182617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41493427753448486},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.39745208621025085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3327648937702179},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.24665188789367676}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8805458545684814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785132646560669},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7105202674865723},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.6043311953544617},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.601753294467926},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5909205079078674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5027186870574951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48799413442611694},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.46851515769958496},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.44878721237182617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41493427753448486},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.39745208621025085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327648937702179},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.24665188789367676},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/pra2.2017.14505401056","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pra2.2017.14505401056","pdf_url":null,"source":{"id":"https://openalex.org/S4393918545","display_name":"Proceedings of the Association for Information Science and Technology","issn_l":"2373-9231","issn":["2373-9231"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Association for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W2015623780","https://openalex.org/W2063392856","https://openalex.org/W2073459066","https://openalex.org/W2095897464","https://openalex.org/W2138615112","https://openalex.org/W2157814774","https://openalex.org/W2165232124","https://openalex.org/W2165612380","https://openalex.org/W2248037989","https://openalex.org/W2251117789","https://openalex.org/W2251863293","https://openalex.org/W2562500328","https://openalex.org/W4231029117","https://openalex.org/W4237791300"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W4309228610","https://openalex.org/W4294597112"],"abstract_inverted_index":{"ABSTRACT":[0],"Currently,":[1],"the":[2,58,135],"internet":[3],"has":[4,46],"created":[5],"many":[6],"documents":[7,44,54,124,163],"in":[8,33,79],"languages":[9],"other":[10],"than":[11],"English.":[12],"People":[13],"face":[14],"challenges":[15],"when":[16,30,145],"seeking":[17],"and":[18,61,72,100,114,128],"using":[19],"information;":[20],"for":[21,48,66,122,134,161],"example,":[22],"non\u2010native":[23],"English\u2010speaking":[24],"students":[25],"tend":[26],"to":[27,118,155],"have":[28],"problems":[29],"utilizing":[31],"libraries":[32],"North":[34],"American":[35],"universities.":[36],"To":[37],"help":[38],"people":[39],"efficiently":[40],"organize":[41],"information,":[42],"bilingual":[43,123,136],"clustering":[45,73,109,142,151],"advantages":[47],"practical":[49],"utilization,":[50],"it":[51],"can":[52],"divide":[53],"into":[55],"groups":[56],"with":[57,104,150],"same":[59],"topic":[60],"there":[62],"is":[63],"no":[64],"need":[65],"a":[67],"training":[68],"dataset.":[69],"Document":[70],"representation":[71,86,148],"models":[74,160],"are":[75,131],"two":[76],"important":[77,154],"parts":[78],"clustering.":[80,125],"This":[81],"paper":[82],"compares":[83],"four":[84,105],"popular":[85],"methods,":[87],"vector":[88],"space":[89],"model":[90],"(VSM),":[91],"latent":[92,96],"semantic":[93],"indexing":[94],"(LSI),":[95],"Dirichlet":[97],"allocation":[98],"(LDA)":[99],"doc2vec":[101],"(D2V),":[102],"together":[103],"different":[106,147],"types":[107],"of":[108,159],"algorithms,":[110],"K\u2010means++,":[111],"BIRCH,":[112],"DBSCAN":[113],"affinity":[115],"propagation":[116],"(AP)":[117],"identify":[119],"appropriate":[120],"combinations":[121],"Parallel":[126],"corpus":[127,130],"comparable":[129],"all":[132],"used":[133],"datasets.":[137],"Experimental":[138],"results":[139],"show":[140],"that,":[141],"performance":[143],"varies":[144],"combining":[146],"methods":[149],"algorithms.":[152],"It's":[153],"make":[156],"good":[157],"choice":[158],"better":[162],"organization.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}