{"id":"https://openalex.org/W2956301977","doi":"https://doi.org/10.18653/v1/w19-5321","title":"Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation","display_name":"Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2956301977","doi":"https://doi.org/10.18653/v1/w19-5321","mag":"2956301977"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5321","pdf_url":"https://www.aclweb.org/anthology/W19-5321.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 2: Shared Task Papers, Day 1)","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/W19-5321.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Microsoft One Microsoft Way Redmond, WA 98052, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft One Microsoft Way Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065193578"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.3146,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91176289,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"233"},"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":0.9998000264167786,"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/T13629","display_name":"Text Readability and Simplification","score":0.9966999888420105,"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/machine-translation","display_name":"Machine translation","score":0.8449787497520447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343727588653564},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7606704235076904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.686913013458252},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6672499179840088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5829731225967407},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5130085349082947},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44764137268066406},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34968888759613037}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8449787497520447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343727588653564},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7606704235076904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.686913013458252},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6672499179840088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5829731225967407},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5130085349082947},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44764137268066406},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34968888759613037},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5321","pdf_url":"https://www.aclweb.org/anthology/W19-5321.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 2: Shared Task Papers, Day 1)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.06170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.06170","pdf_url":"https://arxiv.org/pdf/1907.06170","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":null,"raw_type":"text"},{"id":"mag:2956301977","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.06170v1","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.1907.06170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.06170","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/w19-5321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5321","pdf_url":"https://www.aclweb.org/anthology/W19-5321.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 2: Shared Task Papers, Day 1)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2956301977.pdf","grobid_xml":"https://content.openalex.org/works/W2956301977.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2889326796","https://openalex.org/W2962802109","https://openalex.org/W2962826395","https://openalex.org/W2963250244","https://openalex.org/W2963281280","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2964240726","https://openalex.org/W2970279348"],"related_works":["https://openalex.org/W2970529093","https://openalex.org/W2964308564","https://openalex.org/W2963403868","https://openalex.org/W2963216553","https://openalex.org/W2885616807","https://openalex.org/W2962712961","https://openalex.org/W3114346548","https://openalex.org/W2969707108","https://openalex.org/W2974940950","https://openalex.org/W3045570277","https://openalex.org/W3118612332","https://openalex.org/W2964121744","https://openalex.org/W2963341956","https://openalex.org/W2101105183","https://openalex.org/W2985671716","https://openalex.org/W1965420956","https://openalex.org/W3022839720","https://openalex.org/W2970792434","https://openalex.org/W3164660882","https://openalex.org/W2952635012"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,8,74,101,120,129,132,153,170],"Microsoft":[4],"Translator":[5],"submissions":[6],"to":[7,49,65,85,166],"WMT19":[9],"news":[10],"translation":[11,23,92],"shared":[12],"task":[13],"for":[14,100,108,119,137],"English-German.":[15],"Our":[16],"main":[17],"focus":[18],"is":[19],"document-level":[20,142,154,162],"neural":[21],"machine":[22],"with":[24,30,52,96,105],"deep":[25],"transformer":[26,91],"models.":[27,93],"We":[28,55,94,114],"start":[29],"strong":[31],"sentence-level":[32,159],"baselines,":[33],"trained":[34],"on":[35,131,145],"large-scale":[36],"data":[37,97,104,111,127],"created":[38],"via":[39,128],"data-filtering":[40],"and":[41,44,61,76,89,107,134,141],"noisy":[42],"back-translation":[43],"find":[45],"that":[46],"backtranslation":[47],"seems":[48],"mainly":[50],"help":[51],"translationese":[53],"input.":[54],"explore":[56,116],"fine-tuning":[57],"techniques,":[58],"deeper":[59],"models":[60],"different":[62],"ensembling":[63],"strategies":[64],"counter":[66],"these":[67],"effects.":[68],"Using":[69],"document":[70],"boundaries":[71],"present":[72],"in":[73,173],"authentic":[75,103,110],"synthetic":[77],"parallel":[78],"data,":[79],"we":[80],"create":[81],"sequences":[82],"of":[83,122,139],"up":[84],"1000":[86],"subword":[87],"segments":[88],"train":[90],"experiment":[95],"augmentation":[98],"techniques":[99],"smaller":[102],"documentboundaries":[106],"larger":[109],"without":[112],"boundaries.":[113],"further":[115],"multi-task":[117],"training":[118],"incorporation":[121],"documentlevel":[123],"source":[124],"language":[125],"monolingual":[126],"BERT-objective":[130],"encoder":[133],"twopass":[135],"decoding":[136],"combinations":[138],"sentencelevel":[140],"systems.":[143],"Based":[144],"preliminary":[146],"human":[147,171],"evaluation":[148],"results,":[149],"evaluators":[150],"strongly":[151],"prefer":[152],"systems":[155,163],"over":[156],"our":[157],"comparable":[158],"system.":[160],"The":[161],"also":[164],"seem":[165],"score":[167],"higher":[168],"than":[169],"references":[172],"source-based":[174],"direct":[175],"assessment.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}