{"id":"https://openalex.org/W2963773505","doi":"https://doi.org/10.18653/v1/d18-1035","title":"A Stable and Effective Learning Strategy for Trainable Greedy Decoding","display_name":"A Stable and Effective Learning Strategy for Trainable Greedy Decoding","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963773505","doi":"https://doi.org/10.18653/v1/d18-1035","mag":"2963773505"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1035","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1035","pdf_url":"https://www.aclweb.org/anthology/D18-1035.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/D18-1035.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100416565","display_name":"Yun Chen","orcid":"https://orcid.org/0000-0002-9934-9979"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Yun Chen","raw_affiliation_strings":["The University of Hong Kong,"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056877599","display_name":"Victor O. K. Li","orcid":"https://orcid.org/0000-0002-1380-9445"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Victor O.K. Li","raw_affiliation_strings":["The University of Hong Kong,"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091175785","display_name":"Kyunghyun Cho","orcid":"https://orcid.org/0000-0003-1669-3211"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["New York University, CIFAR Global Scholar"],"affiliations":[{"raw_affiliation_string":"New York University, CIFAR Global Scholar","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067390670","display_name":"Samuel Bowman","orcid":"https://orcid.org/0000-0002-1510-174X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Bowman","raw_affiliation_strings":["New York University, CIFAR Global Scholar"],"affiliations":[{"raw_affiliation_string":"New York University, CIFAR Global Scholar","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100416565"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.9546,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89846702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"390"},"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":0.9991000294685364,"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":0.9991000294685364,"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":0.8657662272453308},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.8389279842376709},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7020927667617798},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7009649276733398},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6573792695999146},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5957631468772888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5900107622146606},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5447233319282532},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5125415325164795},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4474951922893524},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4318963289260864},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4294258654117584},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3773385286331177},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2103416621685028},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.12435173988342285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657662272453308},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.8389279842376709},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7020927667617798},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7009649276733398},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6573792695999146},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5957631468772888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5900107622146606},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5447233319282532},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5125415325164795},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4474951922893524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4318963289260864},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4294258654117584},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3773385286331177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2103416621685028},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.12435173988342285},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1035","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1035","pdf_url":"https://www.aclweb.org/anthology/D18-1035.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/d18-1035","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1035","pdf_url":"https://www.aclweb.org/anthology/D18-1035.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":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963773505.pdf","grobid_xml":"https://content.openalex.org/works/W2963773505.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1595109586","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W2070150502","https://openalex.org/W2078861931","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2149327368","https://openalex.org/W2157331557","https://openalex.org/W2158614781","https://openalex.org/W2176263492","https://openalex.org/W2251071050","https://openalex.org/W2353655624","https://openalex.org/W2395935897","https://openalex.org/W2508728158","https://openalex.org/W2517953077","https://openalex.org/W2552838200","https://openalex.org/W2557436004","https://openalex.org/W2580192806","https://openalex.org/W2587694128","https://openalex.org/W2594990650","https://openalex.org/W2606974598","https://openalex.org/W2608146174","https://openalex.org/W2610245951","https://openalex.org/W2612675303","https://openalex.org/W2613904329","https://openalex.org/W2757222607","https://openalex.org/W2758162718","https://openalex.org/W2767206889","https://openalex.org/W2866343820","https://openalex.org/W2962784628","https://openalex.org/W2962824887","https://openalex.org/W2962965405","https://openalex.org/W2963141266","https://openalex.org/W2963212250","https://openalex.org/W2963331137","https://openalex.org/W2963403868","https://openalex.org/W2963463964","https://openalex.org/W2963506925","https://openalex.org/W2963551569","https://openalex.org/W2963620441","https://openalex.org/W2963736842","https://openalex.org/W2963768805","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2964352247","https://openalex.org/W4298159529","https://openalex.org/W4301230920","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3204412157","https://openalex.org/W4386269615","https://openalex.org/W4390091683","https://openalex.org/W1994919150","https://openalex.org/W58921990","https://openalex.org/W2204575588","https://openalex.org/W2081821176","https://openalex.org/W2159879965","https://openalex.org/W3084994579","https://openalex.org/W2998661990"],"abstract_inverted_index":{"Beam":[0],"search":[1,7,53,102],"is":[2,70,117],"a":[3,38,64,80,93,104,109,136],"widely":[4],"used":[5],"approximate":[6],"strategy":[8],"for":[9],"neural":[10,66],"network":[11,67],"decoders,":[12],"and":[13,74,130,145,158],"it":[14],"generally":[15],"outperforms":[16],"simple":[17],"greedy":[18],"decoding":[19],"on":[20,103,122,135,141],"tasks":[21],"like":[22,113],"machine":[23],"translation.":[24],"However,":[25],"this":[26,34,85,123],"improvement":[27],"comes":[28],"at":[29],"substantial":[30,153],"computational":[31,58],"cost.":[32,59],"In":[33],"paper,":[35],"we":[36,88],"propose":[37],"flexible":[39],"new":[40],"method":[41,61,116,151],"that":[42,69,149],"allows":[43],"us":[44],"to":[45,72],"reap":[46],"nearly":[47,55],"the":[48,76,90,98,150],"full":[49],"benefits":[50],"of":[51,79,92,100,138],"beam":[52,101],"with":[54],"no":[56,127],"additional":[57],"The":[60],"revolves":[62],"around":[63],"small":[65],"actor":[68,86],"trained":[71,133],"observe":[73],"manipulate":[75],"hidden":[77],"state":[78],"previouslytrained":[81],"decoder.":[82],"To":[83],"train":[84],"network,":[87],"introduce":[89],"use":[91],"pseudo-parallel":[94],"corpus":[95],"built":[96],"using":[97],"output":[99],"base":[105,162],"model,":[106],"ranked":[107],"by":[108,119],"target":[110],"quality":[111,157],"metric":[112],"BLEU.":[114],"Our":[115],"inspired":[118],"earlier":[120],"work":[121],"problem,":[124],"but":[125],"requires":[126],"reinforcement":[128],"learning,":[129],"can":[131],"be":[132],"reliably":[134],"range":[137],"models.":[139],"Experiments":[140],"three":[142,146],"parallel":[143],"corpora":[144],"architectures":[147],"show":[148],"yields":[152],"improvements":[154],"in":[155],"translation":[156],"speed":[159],"over":[160],"each":[161],"system.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}