{"id":"https://openalex.org/W2952918253","doi":"https://doi.org/10.18653/v1/w19-5205","title":"Generalizing Back-Translation in Neural Machine Translation","display_name":"Generalizing Back-Translation in Neural Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952918253","doi":"https://doi.org/10.18653/v1/w19-5205","mag":"2952918253"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5205","pdf_url":"https://www.aclweb.org/anthology/W19-5205.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5205.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113879206","display_name":"Miguel Gra\u00e7a","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Miguel Gra\u00e7a","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005673540","display_name":"Yunsu Kim","orcid":"https://orcid.org/0000-0002-1375-005X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062752026","display_name":"Julian Schamper","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Schamper","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047428600","display_name":"Shahram Khadivi","orcid":"https://orcid.org/0000-0001-5499-6542"},"institutions":[{"id":"https://openalex.org/I1321826891","display_name":"eBay (Ireland)","ror":"https://ror.org/02b00s810","country_code":"IE","type":"company","lineage":["https://openalex.org/I1321826891","https://openalex.org/I4210150719"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Shahram Khadivi","raw_affiliation_strings":["eBay, Inc., Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eBay, Inc., Aachen, Germany","institution_ids":["https://openalex.org/I1321826891"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113879206"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5806,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75391655,"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":null,"last_page":null},"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":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/machine-translation","display_name":"Machine translation","score":0.8678962588310242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7538975477218628},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6796095371246338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6069803833961487},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5138909816741943},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4821448028087616},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.45103299617767334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44904059171676636},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4476189911365509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.392681360244751},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.30300483107566833}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8678962588310242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538975477218628},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6796095371246338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069803833961487},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5138909816741943},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4821448028087616},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.45103299617767334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44904059171676636},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4476189911365509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.392681360244751},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.30300483107566833},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/w19-5205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5205","pdf_url":"https://www.aclweb.org/anthology/W19-5205.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.07286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07286","pdf_url":"https://arxiv.org/pdf/1906.07286","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2952918253","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.07286.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.07286","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.07286","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.18154/rwth-conv-240312","is_oa":true,"landing_page_url":"https://doi.org/10.18154/rwth-conv-240312","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5205","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5205","pdf_url":"https://www.aclweb.org/anthology/W19-5205.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7366229540","display_name":"A Sequence Classification Framework for Human Language Technology","funder_award_id":"694537","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952918253.pdf","grobid_xml":"https://content.openalex.org/works/W2952918253.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1993845689","https://openalex.org/W2006969979","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2144600658","https://openalex.org/W2156985047","https://openalex.org/W2778814079","https://openalex.org/W2790319220","https://openalex.org/W2807995432","https://openalex.org/W2887516053","https://openalex.org/W2902614977","https://openalex.org/W2902786662","https://openalex.org/W2950300355","https://openalex.org/W2952444318","https://openalex.org/W2962784628","https://openalex.org/W2963216553","https://openalex.org/W2963403868"],"related_works":["https://openalex.org/W2970971057","https://openalex.org/W3091044183","https://openalex.org/W2951397374","https://openalex.org/W3018062606","https://openalex.org/W2964093087","https://openalex.org/W3105865624","https://openalex.org/W3028876793","https://openalex.org/W3046481253","https://openalex.org/W2767132955","https://openalex.org/W3015569193","https://openalex.org/W2811277447","https://openalex.org/W2529548870","https://openalex.org/W3143808257","https://openalex.org/W3212388777","https://openalex.org/W2377623075","https://openalex.org/W2740553716","https://openalex.org/W2995538013","https://openalex.org/W2965628207","https://openalex.org/W3034508791","https://openalex.org/W2173094809"],"abstract_inverted_index":{"Back-translation":[0],"-data":[1],"augmentation":[2],"by":[3,77],"translating":[4],"target":[5],"monolingual":[6],"data":[7,50],"-is":[8],"a":[9,56,90],"crucial":[10],"component":[11],"in":[12,24],"modern":[13],"neural":[14],"machine":[15],"translation":[16,105],"(NMT).":[17],"In":[18],"this":[19,61],"work,":[20],"we":[21,63],"reformulate":[22],"back-translation":[23],"the":[25,69,83,99],"scope":[26],"of":[27,30,68],"crossentropy":[28],"optimization":[29],"an":[31],"NMT":[32,58],"model,":[33],"clarifying":[34],"its":[35,42],"underlying":[36],"mathematical":[37],"assumptions":[38],"and":[39,72,86],"approximations":[40],"beyond":[41],"heuristic":[43],"usage.":[44],"Our":[45,94],"formulation":[46],"covers":[47],"broader":[48],"synthetic":[49],"generation":[51],"schemes,":[52],"including":[53],"sampling":[54,88],"from":[55,89],"target-to-source":[57,84],"model.":[59],"With":[60],"formulation,":[62],"point":[64],"out":[65],"fundamental":[66],"problems":[67],"sampling-based":[70],"approaches":[71],"propose":[73],"to":[74],"remedy":[75],"them":[76],"(i)":[78],"disabling":[79],"label":[80],"smoothing":[81],"for":[82],"model":[85],"(ii)":[87],"restricted":[91],"search":[92],"space.":[93],"statements":[95],"are":[96],"investigated":[97],"on":[98],"WMT":[100],"2018":[101],"German":[102],"English":[103],"news":[104],"task.":[106]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}
