{"id":"https://openalex.org/W2944463571","doi":"https://doi.org/10.1109/iscslp.2018.8706667","title":"Multi-Head Attention for End-to-End Neural Machine Translation","display_name":"Multi-Head Attention for End-to-End Neural Machine Translation","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944463571","doi":"https://doi.org/10.1109/iscslp.2018.8706667","mag":"2944463571"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042559717","display_name":"Ivan W. H. Fung","orcid":"https://orcid.org/0000-0002-4396-151X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ivan Fung","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042559717"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70025489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9990000128746033,"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/bleu","display_name":"BLEU","score":0.9210191965103149},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8509131669998169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115220665931702},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6637330055236816},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6011505126953125},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5801934003829956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557989239692688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5037338137626648},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.44652771949768066},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4451749920845032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4080740213394165},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0609154999256134}],"concepts":[{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.9210191965103149},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8509131669998169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115220665931702},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6637330055236816},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6011505126953125},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5801934003829956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557989239692688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5037338137626648},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44652771949768066},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4451749920845032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4080740213394165},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0609154999256134},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical 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},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2018.8706667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-94252","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-94252","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-94252","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2018&rft.spage=&rft.aulast=Fung&rft.aufirst=Ho+Long&rft.atitle=Multi-Head+Attention+for+End-to-End+Neural+Machine+Translation&rft.title=","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1753482797","https://openalex.org/W1902237438","https://openalex.org/W1916559533","https://openalex.org/W2133564696","https://openalex.org/W2146574666","https://openalex.org/W2157331557","https://openalex.org/W2402144811","https://openalex.org/W2550553598","https://openalex.org/W2594990650","https://openalex.org/W2597655663","https://openalex.org/W2626792426","https://openalex.org/W2892009249","https://openalex.org/W2953384591","https://openalex.org/W2962742956","https://openalex.org/W2962788148","https://openalex.org/W2963084773","https://openalex.org/W2963212250","https://openalex.org/W2963386218","https://openalex.org/W2963403868","https://openalex.org/W2963560594","https://openalex.org/W2963564796","https://openalex.org/W2963590118","https://openalex.org/W2963858333","https://openalex.org/W2964308564","https://openalex.org/W3211848854","https://openalex.org/W4295253143","https://openalex.org/W4297733535","https://openalex.org/W4385245566","https://openalex.org/W6637698695","https://openalex.org/W6679434410","https://openalex.org/W6713134421","https://openalex.org/W6735377749","https://openalex.org/W6739811675","https://openalex.org/W6739901393","https://openalex.org/W6746345256","https://openalex.org/W6750638150","https://openalex.org/W6750659034","https://openalex.org/W6751068466","https://openalex.org/W6751097180"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W2395641992","https://openalex.org/W2807475932","https://openalex.org/W3021126373","https://openalex.org/W1915251500","https://openalex.org/W4280571180","https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2426188458","https://openalex.org/W3066373881"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,15,67,77,85,144,149,156,164],"recent":[3],"success":[4],"of":[5,18,47,80,87,93,151,166],"Google's":[6],"Transformer":[7],"model":[8,38,50,146],"works":[9,29],"have":[10,30],"been":[11,56],"done":[12],"on":[13,39,51,76,98,129,174],"borrowing":[14],"novel":[16],"idea":[17,33],"multi-head":[19,64,88,167],"attention":[20,65,168],"to":[21,143],"various":[22],"applications":[23],"under":[24,66],"different":[25],"architectures.":[26],"Albeit":[27],"latest":[28],"adopted":[31],"this":[32,60,154],"using":[34],"an":[35,170],"end-to-end":[36,171],"recurrent":[37,69,172],"speech":[40],"recognition":[41],"and":[42,72,105,115,126,138],"voice":[43],"search,":[44],"making":[45],"use":[46],"a":[48,95,110,133],"similar":[49],"machine":[52,175],"translation":[53,176],"has":[54],"not":[55],"attempted":[57],"yet.":[58],"In":[59],"work,":[61],"we":[62,90,121],"examine":[63],"attention-based":[68],"encoder-decoder":[70],"frame-work,":[71],"conduct":[73],"detailed":[74],"analysis":[75],"positional":[78],"response":[79],"multiple":[81],"heads.":[82],"Through":[83],"leveraging":[84],"essence":[86],"attention,":[89],"are":[91],"capable":[92],"attaining":[94],"state-of-the-art":[96],"result":[97],"IWSLT'":[99],"15":[100],"with":[101],"28.48":[102],"tokenized":[103,124],"BLEU":[104,114,125,137],"53.86%":[106],"TER,":[107],"which":[108,131],"gives":[109],"0.17":[111],"gain":[112,135],"in":[113,118,136,141,169],"0.37%":[116],"reduction":[117,140],"TER.":[119],"Similarly":[120],"achieve":[122],"25.58":[123],"55.03%":[127],"TER":[128,142],"WMT'16,":[130],"provide":[132],"0.40":[134],"0.32%":[139],"baseline":[145],"respectively.":[147],"To":[148],"best":[150],"our":[152],"knowledge,":[153],"is":[155],"first":[157],"work":[158],"<sup":[159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[161],"that":[162],"evaluates":[163],"concept":[165],"network":[173],"tasks.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-05-16T00:00:00"}