{"id":"https://openalex.org/W2962890089","doi":"https://doi.org/10.18653/v1/w18-6314","title":"Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection","display_name":"Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2962890089","doi":"https://doi.org/10.18653/v1/w18-6314","mag":"2962890089"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6314","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6314","pdf_url":"https://www.aclweb.org/anthology/W18-6314.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6314.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100392048","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-6660-5323"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102396915","display_name":"Taro Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taro Watanabe","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067705729","display_name":"Macduff Hughes","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Macduff Hughes","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109037387","display_name":"Tetsuji Nakagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tetsuji Nakagawa","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068010225","display_name":"Ciprian Chelba","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ciprian Chelba","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9944999814033508,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9894999861717224,"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":0.7674203515052795},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.7036934494972229},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6509631872177124},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6409271359443665},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6221470832824707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5910450220108032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5852224826812744},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5484122633934021},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4937673509120941},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4865238070487976},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4829256236553192},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.46912455558776855},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4575897455215454},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4422565698623657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43846699595451355},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4329517185688019},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4165421426296234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3349054455757141},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08937570452690125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07435941696166992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674203515052795},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7036934494972229},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6509631872177124},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6409271359443665},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6221470832824707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5910450220108032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5852224826812744},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5484122633934021},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4937673509120941},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4865238070487976},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4829256236553192},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.46912455558776855},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4575897455215454},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4422565698623657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43846699595451355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4329517185688019},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4165421426296234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3349054455757141},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08937570452690125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07435941696166992},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6314","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6314","pdf_url":"https://www.aclweb.org/anthology/W18-6314.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6314","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6314","pdf_url":"https://www.aclweb.org/anthology/W18-6314.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962890089.pdf","grobid_xml":"https://content.openalex.org/works/W2962890089.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1905522558","https://openalex.org/W2113290770","https://openalex.org/W2115410424","https://openalex.org/W2117278770","https://openalex.org/W2132984949","https://openalex.org/W2296073425","https://openalex.org/W2396575863","https://openalex.org/W2515631395","https://openalex.org/W2525778437","https://openalex.org/W2613904329","https://openalex.org/W2743320544","https://openalex.org/W2750588180","https://openalex.org/W2756978580","https://openalex.org/W2760452458","https://openalex.org/W2903158431","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963919854","https://openalex.org/W2964022663","https://openalex.org/W2964045208","https://openalex.org/W2964265128","https://openalex.org/W3208011254","https://openalex.org/W4298393544","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2990352702","https://openalex.org/W160673860","https://openalex.org/W2963642612","https://openalex.org/W4289548080","https://openalex.org/W1585680390","https://openalex.org/W3173587717","https://openalex.org/W3165456129"],"abstract_inverted_index":{"Measuring":[0],"domain":[1,10,64],"relevance":[2],"of":[3,32,42,92],"data":[4,11,33,43,62,78,86,104],"and":[5,35,60,66,79,89],"identifying":[6],"or":[7],"selecting":[8,61],"well-fit":[9],"for":[12,58,63,99],"machine":[13],"translation":[14],"(MT)":[15],"is":[16,22,26],"a":[17,29,80],"well-studied":[18],"topic,":[19],"but":[20],"denoising":[21,70,81],"not":[23],"yet.":[24],"Denoising":[25],"concerned":[27],"with":[28,105],"different":[30],"type":[31],"quality":[34],"tries":[36],"to":[37,69,101],"reduce":[38],"the":[39,93],"negative":[40],"impact":[41],"noise":[44],"on":[45,103],"MT":[46,51,65],"training,":[47],"in":[48],"particular,":[49],"neural":[50],"(NMT)":[52],"training.":[53,72],"This":[54],"paper":[55],"generalizes":[56],"methods":[57],"measuring":[59],"applies":[67],"them":[68],"NMT":[71,100],"The":[73],"proposed":[74],"approach":[75,94],"uses":[76],"trusted":[77],"curriculum":[82],"realized":[83],"by":[84],"online":[85],"selection.":[87],"Intrinsic":[88],"extrinsic":[90],"evaluations":[91],"show":[95],"its":[96],"significant":[97],"effectiveness":[98],"train":[102],"severe":[106],"noise.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}