{"id":"https://openalex.org/W3089559086","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206990","title":"Dynamic Attention Aggregation with BERT for Neural Machine Translation","display_name":"Dynamic Attention Aggregation with BERT for Neural Machine Translation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089559086","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206990","mag":"3089559086"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5100363740","display_name":"Jiarui Zhang","orcid":"https://orcid.org/0000-0003-1593-444X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"JiaRui Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011137322","display_name":"HongZheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HongZheng Li","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037738790","display_name":"Shumin Shi","orcid":"https://orcid.org/0000-0003-3436-7575"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ShuMin Shi","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HeYan Huang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684459","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0002-4416-3974"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101086828","display_name":"Xiangpeng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XiangPeng Wei","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100363740"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.1353,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5648986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":1.0,"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":0.9988999962806702,"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":0.8677800893783569},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.81308513879776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6126924157142639},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5999814867973328},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5329849123954773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5127345323562622},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4558793604373932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3686469495296478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677800893783569},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.81308513879776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6126924157142639},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5999814867973328},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5329849123954773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127345323562622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4558793604373932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686469495296478},{"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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1026270304","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2113839990","https://openalex.org/W2124807415","https://openalex.org/W2126725946","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2184135559","https://openalex.org/W2250539671","https://openalex.org/W2581377246","https://openalex.org/W2817535134","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2922709902","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2944815030","https://openalex.org/W2946417913","https://openalex.org/W2948947170","https://openalex.org/W2950112473","https://openalex.org/W2950621961","https://openalex.org/W2952468927","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962931466","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963490187","https://openalex.org/W2964067969","https://openalex.org/W2964121744","https://openalex.org/W2964190861","https://openalex.org/W2964308564","https://openalex.org/W2965373594","https://openalex.org/W2968917279","https://openalex.org/W2970597249","https://openalex.org/W2986562961","https://openalex.org/W2994689640","https://openalex.org/W2994928925","https://openalex.org/W2996854111","https://openalex.org/W2997518171","https://openalex.org/W2997763445","https://openalex.org/W3006381853","https://openalex.org/W3011411500","https://openalex.org/W3041866211","https://openalex.org/W4294170691","https://openalex.org/W4297798436","https://openalex.org/W4385245566","https://openalex.org/W6626481562","https://openalex.org/W6631190155","https://openalex.org/W6638575559","https://openalex.org/W6640212811","https://openalex.org/W6677258307","https://openalex.org/W6679155404","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682691769","https://openalex.org/W6686282164","https://openalex.org/W6732696085","https://openalex.org/W6739901393","https://openalex.org/W6746718606","https://openalex.org/W6752830811","https://openalex.org/W6755207826","https://openalex.org/W6759455113","https://openalex.org/W6762521896","https://openalex.org/W6763701032","https://openalex.org/W6765807869","https://openalex.org/W6766673545","https://openalex.org/W6767164110","https://openalex.org/W6767254905","https://openalex.org/W6771175319","https://openalex.org/W6771662605","https://openalex.org/W6771713106","https://openalex.org/W6780039898","https://openalex.org/W6780226713","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W4287236333","https://openalex.org/W4387896177","https://openalex.org/W2140798747","https://openalex.org/W4385557855","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"The":[0],"recently":[1],"proposed":[2,134],"BERT":[3,38,97],"has":[4],"demonstrated":[5],"great":[6],"power":[7],"in":[8],"various":[9],"natural":[10],"language":[11],"processing":[12],"tasks.":[13,142],"However,":[14],"the":[15,60,88,91,95,99,117,140],"model":[16,135],"does":[17],"not":[18],"perform":[19],"effectively":[20],"on":[21,25,105,116,139],"cross-lingual":[22],"tasks,":[23],"especially":[24],"machine":[26,41],"translation.":[27],"In":[28],"this":[29],"work,":[30],"we":[31],"propose":[32],"three":[33],"methods":[34],"to":[35,58,71,85,128],"introduce":[36],"pre-trained":[37,96],"into":[39],"neural":[40],"translation":[42,107],"without":[43],"fine-tuning.":[44],"Our":[45],"approach":[46],"consists":[47],"of":[48,63,90],"a)":[49],"a":[50,55,66,82,129],"linear-attention":[51],"aggregation":[52,68,84,125],"that":[53],"leverages":[54],"parameter":[56],"matrix":[57],"capture":[59],"key":[61],"knowledge":[62],"BERT,":[64],"b)":[65],"self-attention":[67],"which":[69],"aims":[70],"learn":[72],"what":[73],"is":[74],"vital":[75],"for":[76],"input":[77],"and":[78,80,109],"output,":[79],"c)":[81],"switch-gate":[83,124],"dynamically":[86],"control":[87],"balance":[89],"information":[92],"flowing":[93],"from":[94],"or":[98],"NMT":[100],"model.":[101],"We":[102],"conduct":[103],"experiments":[104],"several":[106],"benchmarks":[108],"substantially":[110],"improve":[111],"over":[112],"2":[113],"BELU":[114],"points":[115],"IWSLT'14":[118],"English":[119],"-":[120],"German":[121],"task":[122],"with":[123],"method":[126],"compared":[127],"strong":[130],"baseline,":[131],"while":[132],"our":[133],"also":[136],"performs":[137],"remarkably":[138],"other":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}