{"id":"https://openalex.org/W2135399361","doi":"https://doi.org/10.3115/1220175.1220319","title":"Multilingual document clustering","display_name":"Multilingual document clustering","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2135399361","doi":"https://doi.org/10.3115/1220175.1220319","mag":"2135399361"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220319","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220319","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220319","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220319","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Soto Montalvo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soto Montalvo","raw_affiliation_strings":["GAVAB Group, URJC","GAVAB Group, URJC,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GAVAB Group, URJC","institution_ids":[]},{"raw_affiliation_string":"GAVAB Group, URJC,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101950210","display_name":"Raquel Mart\u00ednez","orcid":"https://orcid.org/0000-0003-1838-632X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raquel Mart\u00ednez","raw_affiliation_strings":["NLP&IR Group, UNED","NLP&IR Group, UNED,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP&IR Group, UNED","institution_ids":[]},{"raw_affiliation_string":"NLP&IR Group, UNED,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064615378","display_name":"Arantza Casillas","orcid":"https://orcid.org/0000-0003-4248-8182"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Arantza Casillas","raw_affiliation_strings":["UPV-EHU","UPV, EHU#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UPV-EHU","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"UPV, EHU#TAB#","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042675695","display_name":"V\u00edctor Fresno","orcid":"https://orcid.org/0000-0003-4270-2628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V\u00edctor Fresno","raw_affiliation_strings":["GAVAB Group, URJC","GAVAB Group, URJC,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GAVAB Group, URJC","institution_ids":[]},{"raw_affiliation_string":"GAVAB Group, URJC,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3314,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89756886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1145","last_page":"1152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9969000220298767,"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":0.9937000274658203,"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":0.8414506912231445},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.810978353023529},{"id":"https://openalex.org/keywords/cognate","display_name":"Cognate","score":0.8075835704803467},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6694638133049011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6617913842201233},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6216546297073364},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5930781960487366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849816799163818},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40907901525497437},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14988085627555847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414506912231445},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.810978353023529},{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.8075835704803467},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6694638133049011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6617913842201233},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6216546297073364},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5930781960487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849816799163818},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40907901525497437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14988085627555847},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1220175.1220319","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220319","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220319","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220319","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220319","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220319","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135399361.pdf","grobid_xml":"https://content.openalex.org/works/W2135399361.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W78076044","https://openalex.org/W78284816","https://openalex.org/W113396932","https://openalex.org/W123309796","https://openalex.org/W1486958347","https://openalex.org/W1508790847","https://openalex.org/W1937758960","https://openalex.org/W2016181719","https://openalex.org/W2038124402","https://openalex.org/W2092094655","https://openalex.org/W2125119195","https://openalex.org/W4239303268"],"related_works":["https://openalex.org/W2356815520","https://openalex.org/W2360457743","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W1869697984","https://openalex.org/W4237592971","https://openalex.org/W2610418638","https://openalex.org/W2387982377"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"approach":[4,46,81,104],"for":[5,24],"Multilingual":[6],"Document":[7],"Clustering":[8],"in":[9,73,112],"comparable":[10,37,107],"corpora.":[11,38],"The":[12,131],"algorithm":[13,97],"is":[14,47,82],"of":[15,28,35,40,44,64,79,94,109],"heuristic":[16],"nature":[17],"and":[18,114],"it":[19,49,59,84],"uses":[20],"as":[21],"unique":[22],"evidence":[23],"clustering":[25],"the":[26,36,41,62,70,74,80,91,96,121],"identification":[27],"cognate":[29,66],"named":[30,67],"entities":[31,68],"between":[32,69],"both":[33],"sides":[34],"One":[39],"main":[42],"advantages":[43],"this":[45,103],"that":[48,83],"does":[50,85],"not":[51,86],"depend":[52],"on":[53,61],"bilingual":[54],"or":[55],"multilingual":[56],"resources.":[57],"However,":[58],"depends":[60],"possibility":[63],"identifying":[65],"languages":[71],"used":[72],"corpus.":[75],"An":[76],"additional":[77],"advantage":[78],"need":[87],"any":[88],"information":[89],"about":[90],"right":[92],"number":[93],"clusters;":[95],"calculates":[98],"it.":[99],"We":[100],"have":[101,119],"tested":[102],"with":[105,123],"a":[106,124],"corpus":[108],"news":[110],"written":[111],"English":[113],"Spanish.":[115],"In":[116],"addition,":[117],"we":[118],"compared":[120],"results":[122,133],"system":[125],"which":[126],"translates":[127],"selected":[128],"document":[129],"features.":[130],"obtained":[132],"are":[134],"encouraging.":[135]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}