{"id":"https://openalex.org/W3034700448","doi":"https://doi.org/10.24963/ijcai.2020/544","title":"Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating","display_name":"Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034700448","doi":"https://doi.org/10.24963/ijcai.2020/544","mag":"3034700448"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/544","pdf_url":"https://www.ijcai.org/proceedings/2020/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0544.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049783368","display_name":"Hongfei Xu","orcid":"https://orcid.org/0000-0001-8397-1459"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hongfei Xu","raw_affiliation_strings":["German Research Center for Artificial Intelligence","Saarland University","German Research Center for Artificial Intelligence, Germany","Saarland University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055232825","display_name":"Deyi Xiong","orcid":"https://orcid.org/0000-0002-2353-5038"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Xiong","raw_affiliation_strings":["Tianjin University","Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":["German Research Center for Artificial Intelligence","Saarland University","German Research Center for Artificial Intelligence, Germany","Saarland University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056590711","display_name":"Qiuhui Liu","orcid":"https://orcid.org/0000-0002-6936-4107"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuhui Liu","raw_affiliation_strings":["China Mobile Online Services","China Mobile Online Services, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Online Services","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Online Services, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3933","last_page":"3940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9933000206947327,"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":0.9678000211715698,"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":0.8680254220962524},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7810176014900208},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6797579526901245},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6456904411315918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5513272285461426},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5437296032905579},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5435085892677307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4852006733417511},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4686669111251831},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46745046973228455},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4455738365650177},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4256947636604309},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41894134879112244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4002463221549988},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11750802397727966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8680254220962524},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7810176014900208},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6797579526901245},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6456904411315918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5513272285461426},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5437296032905579},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5435085892677307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4852006733417511},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4686669111251831},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46745046973228455},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4455738365650177},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4256947636604309},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41894134879112244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4002463221549988},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11750802397727966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/544","pdf_url":"https://www.ijcai.org/proceedings/2020/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/544","pdf_url":"https://www.ijcai.org/proceedings/2020/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3699583840","display_name":null,"funder_award_id":"19JCZDJC31400","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G4444951618","display_name":null,"funder_award_id":"01IW17001","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G5972996833","display_name":null,"funder_award_id":"61861130364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034700448.pdf","grobid_xml":"https://content.openalex.org/works/W3034700448.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2799051177","https://openalex.org/W2806412155","https://openalex.org/W2808508619","https://openalex.org/W2888159079","https://openalex.org/W2888520903","https://openalex.org/W2891534142","https://openalex.org/W2921311659","https://openalex.org/W2952446148","https://openalex.org/W2962712961","https://openalex.org/W2962739339","https://openalex.org/W2962802109","https://openalex.org/W2962931466","https://openalex.org/W2962943802","https://openalex.org/W2963693355","https://openalex.org/W2963842551","https://openalex.org/W2964093087","https://openalex.org/W2964202354","https://openalex.org/W2964289193","https://openalex.org/W2965575120","https://openalex.org/W2970820321","https://openalex.org/W2971278086","https://openalex.org/W2971347700","https://openalex.org/W4300428972","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2275988210"],"abstract_inverted_index":{"Existing":[0],"Neural":[1],"Machine":[2],"Translation":[3],"(NMT)":[4],"systems":[5],"are":[6,21],"generally":[7],"trained":[8],"on":[9,67,100,213],"a":[10,52,68,75,131,136,187,191],"large":[11],"amount":[12],"of":[13,55,82,97,118,130,153,159],"sentence-level":[14,71,101,111,133],"parallel":[15,48,57],"data,":[16],"and":[17,60,113,143,164,171,177,180,190,218,226],"during":[18],"prediction":[19],"sentences":[20],"independently":[22],"translated,":[23],"ignoring":[24],"cross-sentence":[25],"contextual":[26,104],"information.":[27],"This":[28],"leads":[29],"to":[30,37,93,145,169,181],"inconsistency":[31],"between":[32],"translated":[33],"sentences.":[34],"In":[35,88],"order":[36],"address":[38],"this":[39,89],"issue,":[40],"context-aware":[41,64,202],"models":[42,65],"have":[43],"been":[44],"proposed.":[45],"However,":[46],"document-level":[47],"data":[49,58,102,217],"constitutes":[50],"only":[51],"small":[53],"part":[54],"the":[56,95,110,116,174,206,214],"available,":[59],"many":[61],"approaches":[62,84],"build":[63],"based":[66],"pre-trained":[69,99,132,154],"frozen":[70],"translation":[72],"model":[73,204],"in":[74,103,121,139,198,224],"two-step":[76],"training":[77,225],"manner.":[78],"The":[79],"computational":[80],"cost":[81,117],"these":[83],"is":[85,219],"usually":[86],"high.":[87],"paper,":[90],"we":[91,167],"propose":[92,144,168],"make":[94],"most":[96],"layers":[98,129],"representation":[105],"learning,":[106],"reusing":[107],"representations":[108,126,185],"from":[109,127],"Transformer":[112,203],"significantly":[114],"reducing":[115],"incorporating":[119],"contexts":[120,179],"translation.":[122],"We":[123],"find":[124],"that":[125],"shallow":[128],"encoder":[134,155],"play":[135],"vital":[137],"role":[138],"source":[140,147,162,175],"context":[141,148,163,184,199],"encoding,":[142,166],"perform":[146],"encoding":[149],"upon":[150],"weighted":[151],"combinations":[152],"layers'":[156],"outputs.":[157],"Instead":[158],"separately":[160],"performing":[161],"input":[165,176],"iteratively":[170],"jointly":[172],"encode":[173],"its":[178],"generate":[182],"input-aware":[183],"with":[186],"cross-attention":[188],"layer":[189],"gating":[192],"mechanism,":[193],"which":[194],"resets":[195],"irrelevant":[196],"information":[197],"encoding.":[200],"Our":[201],"outperforms":[205],"recent":[207],"CADec":[208],"[Voita":[209],"et":[210],"al.,":[211],"2019c]":[212],"English-Russian":[215],"subtitle":[216],"about":[220],"twice":[221],"as":[222],"fast":[223],"decoding.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}