{"id":"https://openalex.org/W2888555799","doi":"https://doi.org/10.18653/v1/d18-1332","title":"Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation","display_name":"Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888555799","doi":"https://doi.org/10.18653/v1/d18-1332","mag":"2888555799"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1332","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1332","pdf_url":"https://www.aclweb.org/anthology/D18-1332.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1332.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018769709","display_name":"Nikolay Bogoychev","orcid":"https://orcid.org/0000-0003-4373-5261"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolay Bogoychev","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112924039","display_name":"Alham Fikri Aji","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alham Fikri Aji","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065193578","display_name":"Marcin Junczys-Dowmunt","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Microsoft, 1 Microsoft Way, Redmond, WA 98121, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, 1 Microsoft Way, Redmond, WA 98121, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2991","last_page":"2996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.9975000023841858,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.8821313381195068},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.825467586517334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7709833383560181},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7212541699409485},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6501590609550476},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6344817876815796},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6221381425857544},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5194194316864014},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.5109835863113403},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35616517066955566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3283161520957947},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3157355487346649},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.20943671464920044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12716630101203918}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8821313381195068},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.825467586517334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709833383560181},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7212541699409485},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6501590609550476},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6344817876815796},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6221381425857544},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5194194316864014},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.5109835863113403},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35616517066955566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3283161520957947},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3157355487346649},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.20943671464920044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12716630101203918},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d18-1332","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1332","pdf_url":"https://www.aclweb.org/anthology/D18-1332.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"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d58b039c-6b7f-4177-94c9-ffed25ccda90","is_oa":true,"landing_page_url":"http://aclweb.org/anthology/D18-1332","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1332","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1332","pdf_url":"https://www.aclweb.org/anthology/D18-1332.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":[{"score":0.7599999904632568,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888555799.pdf","grobid_xml":"https://content.openalex.org/works/W2888555799.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1845277745","https://openalex.org/W2130062883","https://openalex.org/W2133564696","https://openalex.org/W2138243089","https://openalex.org/W2418388682","https://openalex.org/W2436522418","https://openalex.org/W2512924740","https://openalex.org/W2622263826","https://openalex.org/W2740433069","https://openalex.org/W2774000609","https://openalex.org/W2797328513","https://openalex.org/W2798687821","https://openalex.org/W2888206291","https://openalex.org/W2949692215","https://openalex.org/W2951781666","https://openalex.org/W2953384591","https://openalex.org/W2962801832","https://openalex.org/W2963679688","https://openalex.org/W2963803379","https://openalex.org/W2963959597","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2964343359","https://openalex.org/W2994779554","https://openalex.org/W3101036738","https://openalex.org/W3136506209","https://openalex.org/W4293569541","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2168758875","https://openalex.org/W2410733619","https://openalex.org/W4246549241","https://openalex.org/W2963483475","https://openalex.org/W1876383975","https://openalex.org/W2966297898","https://openalex.org/W2955229517","https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816"],"abstract_inverted_index":{"In":[0,25],"order":[1,26],"to":[2,27,89],"extract":[3],"the":[4,16,21,41,46,53,65,75],"best":[5],"possible":[6],"performance":[7],"from":[8],"asynchronous":[9,58],"stochastic":[10,59],"gradient":[11,37,55,60,77],"descent":[12,61],"one":[13],"must":[14],"increase":[15,47],"mini-batch":[17,42,49],"size":[18,50],"and":[19,79],"scale":[20],"learning":[22],"rate":[23],"accordingly.":[24],"achieve":[28],"further":[29],"speedup":[30],"we":[31,51,86],"introduce":[32,70],"a":[33,91],"technique":[34],"that":[35],"delays":[36],"updates":[38],"effectively":[39],"increasing":[40],"size.":[43],"Unfortunately":[44],"with":[45,81,102],"of":[48],"worsen":[52],"stale":[54,76],"problem":[56,78],"in":[57,105],"(SGD)":[62],"which":[63,73],"makes":[64],"model":[66],"convergence":[67],"poor.":[68],"We":[69],"local":[71],"optimizers":[72],"mitigate":[74],"together":[80],"fine":[82],"tuning":[83],"our":[84],"momentum":[85],"are":[87],"able":[88],"train":[90],"shallow":[92],"machine":[93],"translation":[94],"system":[95],"27%":[96],"faster":[97],"than":[98],"an":[99],"optimized":[100],"baseline":[101],"negligible":[103],"penalty":[104],"BLEU.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}