{"id":"https://openalex.org/W1902237438","doi":"https://doi.org/10.18653/v1/d15-1166","title":"Effective Approaches to Attention-based Neural Machine Translation","display_name":"Effective Approaches to Attention-based Neural Machine Translation","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1902237438","doi":"https://doi.org/10.18653/v1/d15-1166","mag":"1902237438"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1166","pdf_url":"https://www.aclweb.org/anthology/D15-1166.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1166.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013286997","display_name":"Thang Luong","orcid":"https://orcid.org/0009-0001-7202-8016"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thang Luong","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101426340","display_name":"Hieu Pham","orcid":"https://orcid.org/0000-0001-7704-5053"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hieu Pham","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA 94305","Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA 94305","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA 94305","Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA 94305","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8600,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1412","last_page":"1421"},"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":0.9997000098228455,"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":0.9991999864578247,"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/machine-translation","display_name":"Machine translation","score":0.7814456224441528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443816661834717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5830084085464478},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5142380595207214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4197998642921448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.327613890171051},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07046771049499512}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7814456224441528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443816661834717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830084085464478},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5142380595207214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4197998642921448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.327613890171051},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07046771049499512},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d15-1166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1166","pdf_url":"https://www.aclweb.org/anthology/D15-1166.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1166","pdf_url":"https://www.aclweb.org/anthology/D15-1166.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G5801408398","display_name":null,"funder_award_id":"Tesla K40","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"}],"funders":[{"id":"https://openalex.org/F4320307921","display_name":"Bloomberg L.P.","ror":"https://ror.org/02rdpzb15"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1902237438.pdf","grobid_xml":"https://content.openalex.org/works/W1902237438.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1586532344","https://openalex.org/W1591801644","https://openalex.org/W1753482797","https://openalex.org/W2086202918","https://openalex.org/W2100664567","https://openalex.org/W2101105183","https://openalex.org/W2118434577","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2147527908","https://openalex.org/W2153653739","https://openalex.org/W2157331557","https://openalex.org/W2169724380","https://openalex.org/W2250653840","https://openalex.org/W2950178297","https://openalex.org/W2951527505","https://openalex.org/W2962741254","https://openalex.org/W2964308564","https://openalex.org/W4241645538"],"related_works":["https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W1484029852","https://openalex.org/W4379525811","https://openalex.org/W2167662847","https://openalex.org/W193726211","https://openalex.org/W3198474835","https://openalex.org/W1569841287","https://openalex.org/W2140460368","https://openalex.org/W1978161643"],"abstract_inverted_index":{"An":[0],"attentional":[1,45],"mechanism":[2],"has":[3,26],"lately":[4],"been":[5,27],"used":[6],"to":[7,53,131],"improve":[8],"neural":[9],"machine":[10],"translation":[11,83,133],"(NMT)":[12],"by":[13,151],"selectively":[14],"focusing":[15],"on":[16,80],"parts":[17],"of":[18,44,67,77,100,141],"the":[19,75,81,128,146],"source":[20,55,68],"sentence":[21],"during":[22],"translation.":[23],"However,":[24],"there":[25],"little":[28],"work":[29],"exploring":[30],"useful":[31],"architectures":[32,121],"for":[33],"attention-based":[34],"NMT.":[35],"This":[36],"paper":[37],"examines":[38],"two":[39],"simple":[40],"and":[41,57,87,153],"effective":[42],"classes":[43],"mechanism:":[46],"a":[47,58,65,71,97,123],"global":[48],"approach":[49],"which":[50],"always":[51],"attends":[52],"all":[54],"words":[56,69],"local":[59,93],"one":[60],"that":[61,107],"only":[62],"looks":[63],"at":[64,70],"subset":[66],"time.":[72],"We":[73],"demonstrate":[74],"effectiveness":[76],"both":[78,90],"approaches":[79],"WMT":[82],"tasks":[84],"between":[85],"English":[86,130],"German":[88,132],"in":[89,127],"directions.":[91],"With":[92],"attention,":[94],"we":[95],"achieve":[96],"significant":[98],"gain":[99],"5.0":[101],"BLEU":[102,137,143],"points":[103,144],"over":[104,145],"non-attentional":[105],"systems":[106],"already":[108],"incorporate":[109],"known":[110],"techniques":[111],"such":[112],"as":[113],"dropout.":[114],"Our":[115],"ensemble":[116],"model":[117],"using":[118],"different":[119],"attention":[120],"yields":[122],"new":[124],"state-of-the-art":[125],"result":[126],"WMT'15":[129],"task":[134],"with":[135],"25.9":[136],"points,":[138],"an":[139,154],"improvement":[140],"1.0":[142],"existing":[147],"best":[148],"system":[149],"backed":[150],"NMT":[152],"n-gram":[155],"reranker.":[156],"1":[157]},"counts_by_year":[{"year":2026,"cited_by_count":115},{"year":2025,"cited_by_count":426},{"year":2024,"cited_by_count":558},{"year":2023,"cited_by_count":809},{"year":2022,"cited_by_count":933},{"year":2021,"cited_by_count":1395},{"year":2020,"cited_by_count":1464},{"year":2019,"cited_by_count":1477},{"year":2018,"cited_by_count":881},{"year":2017,"cited_by_count":377},{"year":2016,"cited_by_count":155},{"year":2015,"cited_by_count":9},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}