{"id":"https://openalex.org/W3171828397","doi":"https://doi.org/10.18653/v1/2021.naacl-main.311","title":"Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios","display_name":"Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3171828397","doi":"https://doi.org/10.18653/v1/2021.naacl-main.311","mag":"3171828397"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.naacl-main.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.311","pdf_url":"https://aclanthology.org/2021.naacl-main.311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.naacl-main.311.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023868584","display_name":"Haipeng Sun","orcid":"https://orcid.org/0000-0002-5899-0401"},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Sun","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","JD AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431149","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-8007-2503"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006323375","display_name":"Kehai Chen","orcid":"https://orcid.org/0000-0002-4346-7618"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kehai Chen","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021667085","display_name":"Masao Utiyama","orcid":"https://orcid.org/0000-0003-1111-9245"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masao Utiyama","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033318800","display_name":"Eiichiro Sumita","orcid":"https://orcid.org/0000-0002-1028-4399"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiichiro Sumita","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"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":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67305963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3975","last_page":"3981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T13629","display_name":"Text Readability and Simplification","score":0.9643999934196472,"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/training","display_name":"Training (meteorology)","score":0.7388481497764587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7096530199050903},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7076513767242432},{"id":"https://openalex.org/keywords/chen","display_name":"Chen","score":0.6997050642967224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5994418263435364},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5403355360031128},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.5234091877937317},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47190648317337036},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4679151177406311},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42522504925727844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40522852540016174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38084688782691956}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7388481497764587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096530199050903},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7076513767242432},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.6997050642967224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5994418263435364},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5403355360031128},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.5234091877937317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47190648317337036},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4679151177406311},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42522504925727844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40522852540016174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38084688782691956},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.naacl-main.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.311","pdf_url":"https://aclanthology.org/2021.naacl-main.311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.naacl-main.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.311","pdf_url":"https://aclanthology.org/2021.naacl-main.311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7222400979","display_name":null,"funder_award_id":"JPMI00316","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"}],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3171828397.pdf","grobid_xml":"https://content.openalex.org/works/W3171828397.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2101210369","https://openalex.org/W2111316763","https://openalex.org/W2145094598","https://openalex.org/W2163568299","https://openalex.org/W2561274697","https://openalex.org/W2595715041","https://openalex.org/W2798931235","https://openalex.org/W2914120296","https://openalex.org/W2932618389","https://openalex.org/W2944815030","https://openalex.org/W2950428495","https://openalex.org/W2952468927","https://openalex.org/W2962784628","https://openalex.org/W2962824887","https://openalex.org/W2963216553","https://openalex.org/W2963602293","https://openalex.org/W2964013027","https://openalex.org/W2964121744","https://openalex.org/W2976223659","https://openalex.org/W2995746049","https://openalex.org/W2997574889","https://openalex.org/W3011824510","https://openalex.org/W3034906024","https://openalex.org/W4298393544"],"related_works":["https://openalex.org/W2370310922","https://openalex.org/W2386975637","https://openalex.org/W2891436901","https://openalex.org/W2388837937","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2990352702"],"abstract_inverted_index":{"Haipeng":[0],"Sun,":[1],"Rui":[2],"Wang,":[3],"Kehai":[4],"Chen,":[5],"Masao":[6],"Utiyama,":[7],"Eiichiro":[8],"Sumita,":[9],"Tiejun":[10],"Zhao.":[11],"Proceedings":[12],"of":[13,17,22],"the":[14,18,23],"2021":[15],"Conference":[16],"North":[19],"American":[20],"Chapter":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics:":[27],"Human":[28],"Language":[29],"Technologies.":[30],"2021.":[31]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
