{"id":"https://openalex.org/W2888442053","doi":"https://doi.org/10.18653/v1/d18-1397","title":"A Study of Reinforcement Learning for Neural Machine Translation","display_name":"A Study of Reinforcement Learning for Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888442053","doi":"https://doi.org/10.18653/v1/d18-1397","mag":"2888442053"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1397","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1397","pdf_url":"https://www.aclweb.org/anthology/D18-1397.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1397.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275673","display_name":"Fei Tian","orcid":"https://orcid.org/0000-0003-4345-3125"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Fei Tian","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034685928","display_name":"Jianhuang Lai","orcid":"https://orcid.org/0000-0003-3883-2024"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhuang Lai","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102750692"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":17.4001,"has_fulltext":true,"cited_by_count":159,"citation_normalized_percentile":{"value":0.99263808,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3612","last_page":"3621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9932000041007996,"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":0.8702669739723206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8262383341789246},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8149139881134033},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7263171672821045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6588480472564697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.528324544429779},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5262811779975891},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5130559206008911},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42569079995155334},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4218176603317261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4157024323940277},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07423633337020874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8702669739723206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262383341789246},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8149139881134033},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7263171672821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6588480472564697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.528324544429779},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5262811779975891},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5130559206008911},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42569079995155334},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4218176603317261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4157024323940277},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07423633337020874},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1397","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1397","pdf_url":"https://www.aclweb.org/anthology/D18-1397.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"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1397","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1397","pdf_url":"https://www.aclweb.org/anthology/D18-1397.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888442053.pdf","grobid_xml":"https://content.openalex.org/works/W2888442053.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W45604574","https://openalex.org/W1522301498","https://openalex.org/W1524068846","https://openalex.org/W1665214252","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1993666847","https://openalex.org/W2096557251","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2156718681","https://openalex.org/W2176263492","https://openalex.org/W2512924740","https://openalex.org/W2525778437","https://openalex.org/W2546938941","https://openalex.org/W2561274697","https://openalex.org/W2581637843","https://openalex.org/W2597655663","https://openalex.org/W2607987856","https://openalex.org/W2613904329","https://openalex.org/W2740433069","https://openalex.org/W2740707878","https://openalex.org/W2751527518","https://openalex.org/W2752047430","https://openalex.org/W2754517384","https://openalex.org/W2774334615","https://openalex.org/W2785093437","https://openalex.org/W2787802257","https://openalex.org/W2794365787","https://openalex.org/W2889606145","https://openalex.org/W2962784628","https://openalex.org/W2962955856","https://openalex.org/W2963120839","https://openalex.org/W2963163972","https://openalex.org/W2963216553","https://openalex.org/W2963248296","https://openalex.org/W2963386218","https://openalex.org/W2963403868","https://openalex.org/W2963463964","https://openalex.org/W2964121744","https://openalex.org/W2964190861","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2964352247","https://openalex.org/W4298857966","https://openalex.org/W4307459710","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2768698792","https://openalex.org/W2898767136","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4287630611","https://openalex.org/W3094960827"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,92],"reinforcement":[5,67],"learning":[6],"(RL)":[7],"is":[8,30,98,104],"an":[9],"effective":[10],"approach":[11],"for":[12],"improving":[13],"the":[14,90,117],"performance":[15,118,150],"of":[16,74,119],"neural":[17],"machine":[18],"translation":[19,50,144,154],"(NMT)":[20],"system.":[21],"However,":[22],"due":[23],"to":[24,61,87,111,114],"its":[25],"instability,":[26],"successfully":[27],"RL":[28,84,97,113],"training":[29],"challenging,":[31],"especially":[32,146],"in":[33,83,89],"real-world":[34],"systems":[35,121],"where":[36],"deep":[37],"models":[38,65],"and":[39,141],"large":[40],"datasets":[41],"are":[42],"leveraged.":[43],"In":[44],"this":[45],"paper,":[46],"taking":[47],"several":[48,75],"large-scale":[49],"tasks":[51],"as":[52],"testbeds,":[53],"we":[54,106,132],"conduct":[55],"a":[56,71,108,148],"systematic":[57],"study":[58],"on":[59,136,151],"how":[60],"train":[62],"better":[63],"NMT":[64,120],"using":[66],"learning.":[68],"We":[69],"provide":[70],"comprehensive":[72],"comparison":[73],"important":[76],"factors":[77],"(e.g.,":[78],"baseline":[79],"reward,":[80],"reward":[81],"shaping)":[82],"training.":[85],"Furthermore,":[86],"fill":[88],"gap":[91],"it":[93],"remains":[94],"unclear":[95],"whether":[96],"still":[99],"beneficial":[100],"when":[101],"monolingual":[102,125],"data":[103],"used,":[105],"propose":[107],"new":[109],"method":[110],"leverage":[112],"further":[115],"boost":[116],"trained":[122],"with":[123],"source/target":[124],"data.":[126],"By":[127],"integrating":[128],"all":[129],"our":[130],"findings,":[131],"obtain":[133],"competitive":[134],"results":[135],"WMT14":[137],"English-German,":[138],"WMT17":[139,142,152],"English-Chinese,":[140],"Chinese-English":[143,153],"tasks,":[145],"setting":[147],"state-of-the-art":[149],"task.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}