{"id":"https://openalex.org/W2806311723","doi":"https://doi.org/10.18653/v1/w18-6301","title":"Scaling Neural Machine Translation","display_name":"Scaling Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2806311723","doi":"https://doi.org/10.18653/v1/w18-6301","mag":"2806311723"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6301","pdf_url":"https://www.aclweb.org/anthology/W18-6301.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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6301.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"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":["IL","US"],"is_corresponding":false,"raw_author_name":"Myle Ott","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I2252078561","https://openalex.org/I1291425158"]}]},{"author_position":"middle","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/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"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":["IL","US"],"is_corresponding":false,"raw_author_name":"Sergey Edunov","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I2252078561","https://openalex.org/I1291425158"]}]},{"author_position":"middle","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/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"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":["IL","US"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I2252078561","https://openalex.org/I1291425158"]}]},{"author_position":"last","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/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"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":["IL","US"],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York. Google Brain, Mountain View","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I2252078561","https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8406,"has_fulltext":true,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98837101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9957000017166138,"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":0.8318835496902466},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8028247356414795},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7812988758087158},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7299597263336182},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.565592348575592},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5503085851669312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496559739112854},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.49840545654296875},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.49490469694137573},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47259339690208435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3832765221595764},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3336397409439087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33284705877304077},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29489666223526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318835496902466},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8028247356414795},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7812988758087158},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7299597263336182},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.565592348575592},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5503085851669312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496559739112854},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49840545654296875},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.49490469694137573},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47259339690208435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3832765221595764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3336397409439087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33284705877304077},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29489666223526},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-6301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6301","pdf_url":"https://www.aclweb.org/anthology/W18-6301.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"},{"id":"pmh:oai:arXiv.org:1806.00187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.00187","pdf_url":"https://arxiv.org/pdf/1806.00187","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":"text"},{"id":"mag:2806311723","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.00187","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.1806.00187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.00187","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"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6301","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6301","pdf_url":"https://www.aclweb.org/anthology/W18-6301.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2806311723.pdf","grobid_xml":"https://content.openalex.org/works/W2806311723.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1518951372","https://openalex.org/W1825672851","https://openalex.org/W2095705004","https://openalex.org/W2124807415","https://openalex.org/W2149428536","https://openalex.org/W2162390675","https://openalex.org/W2168231600","https://openalex.org/W2399880602","https://openalex.org/W2606974598","https://openalex.org/W2612675303","https://openalex.org/W2613904329","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2763421725","https://openalex.org/W2767989436","https://openalex.org/W2773493195","https://openalex.org/W2789541106","https://openalex.org/W2790319220","https://openalex.org/W2791110811","https://openalex.org/W2797162333","https://openalex.org/W2896060389","https://openalex.org/W2949650786","https://openalex.org/W2952754453","https://openalex.org/W2962784628","https://openalex.org/W2963532001","https://openalex.org/W2963702144","https://openalex.org/W2964121744","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2963403868","https://openalex.org/W2963341956","https://openalex.org/W2962784628","https://openalex.org/W2963807318","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2964308564","https://openalex.org/W2964121744","https://openalex.org/W2963216553","https://openalex.org/W2965373594","https://openalex.org/W2525778437","https://openalex.org/W2130942839","https://openalex.org/W2064675550","https://openalex.org/W1902237438","https://openalex.org/W2964265128","https://openalex.org/W2952509486","https://openalex.org/W2952444318","https://openalex.org/W3030163527","https://openalex.org/W2622263826","https://openalex.org/W2108598243"],"abstract_inverted_index":{"Sequence":[0],"to":[1,9,69],"sequence":[2],"learning":[3],"models":[4],"still":[5],"require":[6],"several":[7],"days":[8],"reach":[10],"state":[11],"of":[12,59,90],"the":[13,57,75,81],"art":[14],"performance":[15],"on":[16,40,74,95],"large":[17,31],"benchmark":[18],"datasets":[19],"using":[20],"a":[21,41,87],"single":[22,42],"machine.":[23],"This":[24],"paper":[25],"shows":[26],"that":[27],"reduced":[28],"precision":[29],"and":[30,48],"batch":[32],"training":[33,36,73],"can":[34],"speedup":[35],"by":[37,72],"nearly":[38],"5x":[39],"8-GPU":[43],"machine":[44],"with":[45],"careful":[46],"tuning":[47],"implementation.":[49],"1":[50],"On":[51,80],"WMT'14":[52,82],"English-German":[53],"translation,":[54],"we":[55,85],"match":[56],"accuracy":[58],"Vaswani":[60],"et":[61],"al.":[62],"(":[63],"We":[64],"further":[65],"improve":[66],"these":[67],"results":[68],"29.8":[70],"BLEU":[71,89],"much":[76],"larger":[77],"Paracrawl":[78],"dataset.":[79],"English-French":[83],"task,":[84],"obtain":[86],"state-of-the-art":[88],"43.2":[91],"in":[92],"8.5":[93],"hours":[94],"128":[96],"GPUs.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
