{"id":"https://openalex.org/W2889326796","doi":"https://doi.org/10.18653/v1/d18-1045","title":"Understanding Back-Translation at Scale","display_name":"Understanding Back-Translation at Scale","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889326796","doi":"https://doi.org/10.18653/v1/d18-1045","mag":"2889326796"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1045","pdf_url":"https://www.aclweb.org/anthology/D18-1045.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1045.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016113002","display_name":"Sergey Edunov","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"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Edunov","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076248976","display_name":"Myle Ott","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"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myle Ott","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"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"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"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"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA & New York, NY. Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":96.6426,"has_fulltext":true,"cited_by_count":1023,"citation_normalized_percentile":{"value":0.99956646,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.8490085005760193},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.813767671585083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6537790894508362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6187857985496521},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5592905282974243},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5371843576431274},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5337352156639099},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5057435035705566},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49906396865844727},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4648280143737793},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4596962034702301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43815428018569946},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4354609549045563},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43075618147850037},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42790910601615906},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4183211922645569},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.41744935512542725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08197930455207825},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0776960551738739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06376039981842041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490085005760193},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.813767671585083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6537790894508362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6187857985496521},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5592905282974243},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5371843576431274},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5337352156639099},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5057435035705566},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49906396865844727},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4648280143737793},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4596962034702301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43815428018569946},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4354609549045563},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43075618147850037},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42790910601615906},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4183211922645569},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.41744935512542725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08197930455207825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0776960551738739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06376039981842041},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1045","pdf_url":"https://www.aclweb.org/anthology/D18-1045.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1045","pdf_url":"https://www.aclweb.org/anthology/D18-1045.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889326796.pdf","grobid_xml":"https://content.openalex.org/works/W2889326796.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W211509693","https://openalex.org/W1522301498","https://openalex.org/W1810943226","https://openalex.org/W1902237438","https://openalex.org/W1915251500","https://openalex.org/W1916559533","https://openalex.org/W2025768430","https://openalex.org/W2097333193","https://openalex.org/W2101105183","https://openalex.org/W2109664771","https://openalex.org/W2122270629","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2136156618","https://openalex.org/W2141440284","https://openalex.org/W2153653739","https://openalex.org/W2157331557","https://openalex.org/W2169200297","https://openalex.org/W2183341477","https://openalex.org/W2540404261","https://openalex.org/W2546938941","https://openalex.org/W2550821151","https://openalex.org/W2555745756","https://openalex.org/W2561274697","https://openalex.org/W2566564022","https://openalex.org/W2581377246","https://openalex.org/W2595715041","https://openalex.org/W2597891111","https://openalex.org/W2612675303","https://openalex.org/W2613904329","https://openalex.org/W2733239165","https://openalex.org/W2756566411","https://openalex.org/W2758310181","https://openalex.org/W2767982226","https://openalex.org/W2767989436","https://openalex.org/W2770173563","https://openalex.org/W2775795276","https://openalex.org/W2794365787","https://openalex.org/W2797913374","https://openalex.org/W2798931235","https://openalex.org/W2806311723","https://openalex.org/W2886095922","https://openalex.org/W2887516053","https://openalex.org/W2953333557","https://openalex.org/W2962784628","https://openalex.org/W2962883855","https://openalex.org/W2963096510","https://openalex.org/W2963216553","https://openalex.org/W2963247703","https://openalex.org/W2963366552","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963569817","https://openalex.org/W2963602293","https://openalex.org/W2963708445","https://openalex.org/W2963768805","https://openalex.org/W2963774520","https://openalex.org/W2963804993","https://openalex.org/W2963807318","https://openalex.org/W2963925437","https://openalex.org/W2963993537","https://openalex.org/W2964007535","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W3211848854","https://openalex.org/W4241645538","https://openalex.org/W4293388793","https://openalex.org/W4297798436","https://openalex.org/W4297801368","https://openalex.org/W4298137069","https://openalex.org/W4298393544","https://openalex.org/W4301368689","https://openalex.org/W4307459710","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W170118632","https://openalex.org/W2518299649","https://openalex.org/W2395641992","https://openalex.org/W2251802443","https://openalex.org/W2807475932","https://openalex.org/W4280571180","https://openalex.org/W3021126373","https://openalex.org/W3066373881","https://openalex.org/W2903057408"],"abstract_inverted_index":{"An":[0],"effective":[1],"method":[2],"to":[3,12,37,92,103],"improve":[4],"neural":[5],"machine":[6],"translation":[7],"with":[8,18],"monolingual":[9,108],"data":[10,70,78,90],"is":[11],"augment":[13],"the":[14,27,116,122],"parallel":[15],"training":[16,75],"corpus":[17],"back-translations":[19,51],"of":[20,29,35,105,107,115,118],"target":[21],"language":[22],"sentences.":[23,41],"This":[24],"work":[25],"broadens":[26],"understanding":[28],"back-translation":[30],"and":[31,95,110],"investigates":[32],"a":[33,72,112],"number":[34],"methods":[36],"generate":[38],"synthetic":[39,69,89],"source":[40],"We":[42,85],"find":[43],"that":[44,65],"in":[45],"all":[46],"but":[47],"resource":[48],"poor":[49],"settings":[50],"obtained":[52],"via":[53],"sampling":[54,66],"or":[55,67,82],"noised":[56],"beam":[57,81],"outputs":[58],"are":[59],"most":[60],"effective.":[61],"Our":[62],"analysis":[63],"shows":[64],"noisy":[68],"gives":[71],"much":[73],"stronger":[74],"signal":[76],"than":[77],"generated":[79],"by":[80],"greedy":[83],"search.":[84],"also":[86],"compare":[87],"how":[88],"compares":[91],"genuine":[93],"bitext":[94],"study":[96],"various":[97],"domain":[98],"effects.":[99],"Finally,":[100],"we":[101],"scale":[102],"hundreds":[104],"millions":[106],"sentences":[109],"achieve":[111],"new":[113],"state":[114],"art":[117],"35":[119],"BLEU":[120],"on":[121],"WMT'14":[123],"English-German":[124],"test":[125],"set.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":73},{"year":2023,"cited_by_count":157},{"year":2022,"cited_by_count":145},{"year":2021,"cited_by_count":221},{"year":2020,"cited_by_count":222},{"year":2019,"cited_by_count":124},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}