{"id":"https://openalex.org/W2538986668","doi":"https://doi.org/10.1145/2983323.2983732","title":"Cross-lingual Text Classification via Model Translation with Limited Dictionaries","display_name":"Cross-lingual Text Classification via Model Translation with Limited Dictionaries","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2538986668","doi":"https://doi.org/10.1145/2983323.2983732","mag":"2538986668"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983732","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983732&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2983732&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102323363","display_name":"Ruochen Xu","orcid":"https://orcid.org/0009-0008-5750-8848"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruochen Xu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542734","display_name":"Yiming Yang","orcid":"https://orcid.org/0009-0006-3569-0023"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981450","display_name":"Hanxiao Liu","orcid":"https://orcid.org/0000-0002-9340-5503"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanxiao Liu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075910805","display_name":"Andrew Hsi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Hsi","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102323363"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.092,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93167301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922999739646912,"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":0.9908000230789185,"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":0.7897956967353821},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7612221240997314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7380431890487671},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5694965720176697},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4540953040122986},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4492361843585968},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.444192498922348},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.44118836522102356},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.42927587032318115},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.2852255702018738},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15716451406478882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897956967353821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7612221240997314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7380431890487671},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5694965720176697},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4540953040122986},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4492361843585968},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.444192498922348},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.44118836522102356},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.42927587032318115},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2852255702018738},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15716451406478882},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983732","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983732&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2983323.2983732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983732","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983732&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1556874163","display_name":"III: Small: Multi-field Hierarchical Discovery and Tracking (mf-HDT) of Emerging Topics","funder_award_id":"1216282","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2581707695","display_name":"BIGDATA: F: Large-Scale Transductive Learning from Heterogeneous Data Sources","funder_award_id":"1546329","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3429874898","display_name":null,"funder_award_id":"LORELEI","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4726163615","display_name":null,"funder_award_id":"IIS-1216282 and IIS-1546329","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5420615920","display_name":null,"funder_award_id":"IIS-1546329","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5432064702","display_name":null,"funder_award_id":"FA8750-12-2-0342","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5447833889","display_name":null,"funder_award_id":"HR0011-15-C-0114 and FA8750-12-2-0342","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8016956108","display_name":null,"funder_award_id":"HR0011-15-C-0114","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2538986668.pdf","grobid_xml":"https://content.openalex.org/works/W2538986668.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W1489959797","https://openalex.org/W1550206324","https://openalex.org/W1614298861","https://openalex.org/W1828724394","https://openalex.org/W1854251030","https://openalex.org/W1980862579","https://openalex.org/W1994966918","https://openalex.org/W2099031744","https://openalex.org/W2118090838","https://openalex.org/W2126725946","https://openalex.org/W2141599568","https://openalex.org/W2142742813","https://openalex.org/W2144945507","https://openalex.org/W2148861942","https://openalex.org/W2150102617","https://openalex.org/W2158199200","https://openalex.org/W2167660864","https://openalex.org/W2250414191","https://openalex.org/W2250741688","https://openalex.org/W2251033195","https://openalex.org/W2251804196","https://openalex.org/W2252212383","https://openalex.org/W2511623037","https://openalex.org/W2559655401","https://openalex.org/W2564663390","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2607662938","https://openalex.org/W2950133940","https://openalex.org/W2962795068"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2962780935","https://openalex.org/W2215759665","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"Cross-lingual":[0],"text":[1],"classification":[2,70,104,136],"(CLTC)":[3],"refers":[4],"to":[5,26,169],"the":[6,15,30,43,53,73,84,88,100],"task":[7],"of":[8,18,45,50,68,102,127,135,150],"classifying":[9],"documents":[10,28,51],"in":[11,23,122,144,155,166],"different":[12,123],"languages":[13,31,54,74],"into":[14],"same":[16],"taxonomy":[17],"categories.":[19],"An":[20],"open":[21],"challenge":[22,86],"CLTC":[24,85,145],"is":[25,93],"classify":[27],"for":[29,65],"where":[32,55,75],"labeled":[33,76],"training":[34,57,77],"data":[35,58,78],"are":[36,59,79],"not":[37],"available.":[38],"Existing":[39],"approaches":[40,116,139],"rely":[41],"on":[42,99,146],"availability":[44],"either":[46],"high-quality":[47],"machine":[48],"translation":[49,67,134],"(to":[52,72],"massively":[56],"available),":[60],"or":[61,177],"rich":[62],"bilingual":[63,109,175],"dictionaries":[64,176],"effective":[66],"trained":[69],"models":[71,105],"lacking).":[80],"This":[81],"paper":[82],"studies":[83],"under":[87],"assumption":[89],"that":[90,117],"neither":[91],"condition":[92],"met.":[94],"That":[95],"is,":[96],"we":[97,112],"focus":[98],"problem":[101],"translating":[103],"with":[106],"highly":[107,178],"incomplete":[108,179],"dictionaries.":[110],"Specifically,":[111],"propose":[113],"two":[114],"new":[115],"combines":[118],"unsupervised":[119],"word":[120],"embedding":[121],"languages,":[124,131],"supervised":[125],"mapping":[126],"embedded":[128],"words":[129],"across":[130],"and":[132,160,162],"probabilistic":[133],"models.":[137],"The":[138],"show":[140],"significant":[141],"performance":[142],"improvement":[143],"a":[147],"benchmark":[148],"corpus":[149],"Reuters":[151],"news":[152],"stories":[153],"(RCV1/RCV2)":[154],"English,":[156],"Spanish,":[157],"German,":[158],"French":[159],"Chinese":[161],"an":[163],"internal":[164],"dataset":[165],"Uzbek,":[167],"compared":[168],"representative":[170],"baseline":[171],"methods":[172],"using":[173],"conventional":[174],"ones.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}