{"id":"https://openalex.org/W3034724424","doi":"https://doi.org/10.24963/ijcai.2020/533","title":"CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP","display_name":"CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034724424","doi":"https://doi.org/10.24963/ijcai.2020/533","mag":"3034724424"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/533","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/533","pdf_url":"https://www.ijcai.org/proceedings/2020/0533.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0533.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":["Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003777635","display_name":"Minheng Ni","orcid":"https://orcid.org/0000-0001-6483-0650"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minheng Ni","raw_affiliation_strings":["Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Institute of Advanced Technology, Westlake Institute for Advanced Study","Westlake University","School of Engineering, Westlake University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology, Westlake Institute for Advanced Study","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":131,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3853","last_page":"3860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9807000160217285,"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":0.817771852016449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5908979177474976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554302930831909},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5532804131507874},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.53431636095047},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5297960638999939},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5032560229301453},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4954131841659546},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.492636501789093},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.48591819405555725},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4159836769104004},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15476956963539124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14760759472846985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12038242816925049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817771852016449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5908979177474976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554302930831909},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5532804131507874},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.53431636095047},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5297960638999939},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5032560229301453},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4954131841659546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.492636501789093},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.48591819405555725},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4159836769104004},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15476956963539124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14760759472846985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12038242816925049},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/533","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/533","pdf_url":"https://www.ijcai.org/proceedings/2020/0533.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/533","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/533","pdf_url":"https://www.ijcai.org/proceedings/2020/0533.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G1649532842","display_name":null,"funder_award_id":"61976072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4165806713","display_name":null,"funder_award_id":"61632011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8903434528","display_name":"\u9762\u5411\u804a\u5929\u673a\u5668\u4eba\u7684\u6587\u672c\u60c5\u611f\u5206\u6790\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034724424.pdf","grobid_xml":"https://content.openalex.org/works/W3034724424.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2144945507","https://openalex.org/W2251033195","https://openalex.org/W2294774419","https://openalex.org/W2564663390","https://openalex.org/W2620558438","https://openalex.org/W2762484717","https://openalex.org/W2799052853","https://openalex.org/W2885323099","https://openalex.org/W2885519967","https://openalex.org/W2891555348","https://openalex.org/W2896457183","https://openalex.org/W2898856000","https://openalex.org/W2915128308","https://openalex.org/W2939455697","https://openalex.org/W2949604985","https://openalex.org/W2962738716","https://openalex.org/W2963721344","https://openalex.org/W2963793519","https://openalex.org/W2965373594","https://openalex.org/W2970850076","https://openalex.org/W2971133142","https://openalex.org/W2971207485","https://openalex.org/W2973088264","https://openalex.org/W2997214274","https://openalex.org/W2998572029","https://openalex.org/W3034469191","https://openalex.org/W3104723404","https://openalex.org/W4299579390","https://openalex.org/W6751459940","https://openalex.org/W6767737316","https://openalex.org/W6791858558","https://openalex.org/W6863994431","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W4389976243","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2974240475","https://openalex.org/W4388441038"],"abstract_inverted_index":{"Multi-lingual":[0],"contextualized":[1,25],"embeddings,":[2],"such":[3],"as":[4],"multilingual-BERT":[5],"(mBERT),":[6],"have":[7],"shown":[8],"success":[9],"in":[10],"a":[11,45],"variety":[12],"of":[13,27],"zero-shot":[14],"cross-lingual":[15],"tasks.":[16],"However,":[17],"these":[18],"models":[19],"are":[20],"limited":[21],"by":[22,37,70],"having":[23],"inconsistent":[24],"representations":[26,62],"subwords":[28],"across":[29],"different":[30],"languages.":[31,99],"Existing":[32],"work":[33],"addresses":[34],"this":[35],"issue":[36],"bilingual":[38,86],"projection":[39],"and":[40,65,90],"fine-tuning":[41],"technique.":[42],"We":[43],"propose":[44],"data":[46,53],"augmentation":[47],"framework":[48],"to":[49,54,60,113],"generate":[50],"multi-lingual":[51],"code-switching":[52],"fine-tune":[55],"mBERT,":[56],"which":[57],"encourages":[58],"model":[59],"align":[61],"from":[63],"source":[64],"multiple":[66,97],"target":[67,98],"languages":[68,107],"once":[69],"mixing":[71],"their":[72],"context":[73],"information.":[74],"Compared":[75],"with":[76,105,122],"the":[77,119],"existing":[78],"work,":[79],"our":[80,110],"method":[81,111],"does":[82],"not":[83],"rely":[84],"on":[85,102],"sentences":[87],"for":[88,96,117],"training,":[89],"requires":[91],"only":[92],"one":[93],"training":[94],"process":[95],"Experimental":[100],"results":[101],"five":[103],"tasks":[104,120],"19":[106],"show":[108],"that":[109],"leads":[112],"significantly":[114],"improved":[115],"performances":[116],"all":[118],"compared":[121],"mBERT.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
