{"id":"https://openalex.org/W3165946561","doi":"https://doi.org/10.18653/v1/2021.naacl-main.133","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","display_name":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3165946561","doi":"https://doi.org/10.18653/v1/2021.naacl-main.133","mag":"3165946561"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.naacl-main.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.133","pdf_url":"https://aclanthology.org/2021.naacl-main.133.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.naacl-main.133.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Samuel Kiegeland","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Samuel Kiegeland","raw_affiliation_strings":["Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":null,"display_name":"Julia Kreutzer","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Kreutzer","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.6986,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75655621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1673","last_page":"1681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","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":0.9940000176429749,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6608999967575073},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3853999972343445},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3779999911785126},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571000218391418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.296099990606308},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2021.naacl-main.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.133","pdf_url":"https://aclanthology.org/2021.naacl-main.133.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.08942","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08942","pdf_url":"https://arxiv.org/pdf/2106.08942","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"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.naacl-main.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.133","pdf_url":"https://aclanthology.org/2021.naacl-main.133.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3165946561.pdf","grobid_xml":"https://content.openalex.org/works/W3165946561.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Policy":[0],"gradient":[1],"algorithms":[2],"have":[3,10],"found":[4],"wide":[5],"adoption":[6],"in":[7],"NLP,":[8],"but":[9],"recently":[11],"become":[12],"subject":[13],"to":[14,60],"criticism,":[15],"doubting":[16],"their":[17],"suitability":[18],"for":[19],"NMT.":[20],"Choshen":[21],"et":[22],"al.":[23],"(":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"revisit":[29],"these":[30,61],"claims":[31],"and":[32,45,53,56],"study":[33],"them":[34],"under":[35],"a":[36],"wider":[37],"range":[38],"of":[39,51],"configurations.":[40],"Our":[41],"experiments":[42],"on":[43],"in-domain":[44],"cross-domain":[46],"adaptation":[47],"reveal":[48],"the":[49],"importance":[50],"exploration":[52],"reward":[54],"scaling,":[55],"provide":[57],"empirical":[58],"counterevidence":[59],"claims.":[62]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2021-06-22T00:00:00"}