{"id":"https://openalex.org/W2889964337","doi":"https://doi.org/10.18653/v1/w18-6415","title":"Microsoft\u2019s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data","display_name":"Microsoft\u2019s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889964337","doi":"https://doi.org/10.18653/v1/w18-6415","mag":"2889964337"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6415","pdf_url":"https://www.aclweb.org/anthology/W18-6415.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: Shared Task 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/W18-6415.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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Microsoft 1 Microsoft Way Redmond, WA 98121, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft 1 Microsoft Way Redmond, WA 98121, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065193578"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.0154,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82760426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"425","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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":0.7804087400436401},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7058588862419128},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6134247183799744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5949578881263733},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5894805192947388},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5782444477081299},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5696427226066589},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5319733023643494},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5181382894515991},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.44537946581840515},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44106563925743103},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4269481897354126},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41080474853515625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3248663544654846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3047480583190918},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10216805338859558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804087400436401},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7058588862419128},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6134247183799744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949578881263733},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5894805192947388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5782444477081299},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5696427226066589},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5319733023643494},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5181382894515991},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.44537946581840515},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44106563925743103},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4269481897354126},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41080474853515625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3248663544654846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3047480583190918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10216805338859558},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-6415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6415","pdf_url":"https://www.aclweb.org/anthology/W18-6415.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: Shared Task Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.00196","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.00196","pdf_url":"https://arxiv.org/pdf/1809.00196","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:2889964337","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.00196","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.1809.00196","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.00196","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/w18-6415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6415","pdf_url":"https://www.aclweb.org/anthology/W18-6415.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: Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889964337.pdf","grobid_xml":"https://content.openalex.org/works/W2889964337.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2117278770","https://openalex.org/W2794365787","https://openalex.org/W2902918014","https://openalex.org/W2903193068","https://openalex.org/W2949643137","https://openalex.org/W2950359962","https://openalex.org/W2962784628","https://openalex.org/W2963266340","https://openalex.org/W2963347649","https://openalex.org/W2963403868"],"related_works":["https://openalex.org/W2964240726","https://openalex.org/W2903490366","https://openalex.org/W3120964679","https://openalex.org/W2970210628","https://openalex.org/W2971257618","https://openalex.org/W3214258555","https://openalex.org/W3119684805","https://openalex.org/W3095125651","https://openalex.org/W2970705013","https://openalex.org/W3119961061","https://openalex.org/W2902081112","https://openalex.org/W2418388682","https://openalex.org/W2251979322","https://openalex.org/W3200829979","https://openalex.org/W2902510077","https://openalex.org/W2970947975","https://openalex.org/W2902698002","https://openalex.org/W2903151286","https://openalex.org/W3119262703","https://openalex.org/W2971074957"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,72,86],"Microsoft":[4],"submission":[5],"to":[6,66],"WMT2018":[8],"news":[9],"translation":[10],"shared":[11],"task.":[12],"We":[13,41,100],"participated":[14],"in":[15],"one":[16],"language":[17],"direction":[18],"-English-German.":[19],"Our":[20],"system":[21],"follows":[22],"current":[23],"best-practice":[24],"and":[25,37,57],"combines":[26],"state-of-theart":[27],"models":[28,46],"with":[29,47,59,78],"new":[30],"data":[31,108],"filtering":[32,61],"(dual":[33],"conditional":[34],"cross-entropy":[35],"filtering)":[36],"sentence":[38],"weighting":[39],"methods.":[40],"trained":[42],"fairly":[43],"standard":[44],"Transformer-big":[45],"an":[48],"updated":[49],"version":[50],"of":[51],"Edinburgh's":[52],"training":[53],"scheme":[54],"for":[55,63,75],"WMT2017":[56],"experimented":[58],"different":[60],"schemes":[62],"Paracrawl.":[64],"According":[65],"automatic":[67],"metrics":[68],"(BLEU)":[69],"we":[70,94],"reached":[71],"highest":[73],"score":[74],"this":[76,102],"subtask":[77],"a":[79],"nearly":[80],"2":[81],"BLEU":[82],"point":[83],"margin":[84],"over":[85],"next":[87],"strongest":[88],"system.":[89],"Based":[90],"on":[91],"human":[92],"evaluation":[93],"ranked":[95],"first":[96],"among":[97],"constrained":[98],"systems.":[99],"believe":[101],"is":[103],"mostly":[104],"caused":[105],"by":[106],"our":[107],"filtering/weighting":[109],"regime.":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}