{"id":"https://openalex.org/W4309041555","doi":"https://doi.org/10.1109/taslp.2022.3221040","title":"GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation","display_name":"GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4309041555","doi":"https://doi.org/10.1109/taslp.2022.3221040"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3221040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221040","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100343820","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-1983-012X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1983-012X","affiliations":[{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057453970","display_name":"Yuwei Yin","orcid":"https://orcid.org/0000-0002-5022-6468"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Yin","raw_affiliation_strings":["NLC Team, Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5022-6468","affiliations":[{"raw_affiliation_string":"NLC Team, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003667048","display_name":"Liqun Yang","orcid":"https://orcid.org/0000-0002-3391-4787"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Yang","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3391-4787","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113130010","display_name":"Shuming Ma","orcid":"https://orcid.org/0000-0003-1091-1206"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuming Ma","raw_affiliation_strings":["NLC Team, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLC Team, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020769158","display_name":"Haoyang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Huang","raw_affiliation_strings":["NLC Team, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLC Team, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416386","display_name":"Dongdong Zhang","orcid":"https://orcid.org/0000-0003-0833-7903"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Zhang","raw_affiliation_strings":["NLC Team, Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0833-7903","affiliations":[{"raw_affiliation_string":"NLC Team, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["NLC Team, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLC Team, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036786337","display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9603-9713","affiliations":[{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2803,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93071346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1489","last_page":"1498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6530039310455322},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6184136867523193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5899671316146851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5734356045722961},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5024154186248779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37433382868766785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33363890647888184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2073996663093567},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1225670874118805},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10207533836364746},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08929654955863953}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6530039310455322},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6184136867523193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5899671316146851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734356045722961},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5024154186248779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37433382868766785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33363890647888184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2073996663093567},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1225670874118805},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10207533836364746},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08929654955863953},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3221040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221040","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1363696916","display_name":"\u793e\u4ea4\u7f51\u7edc\u4e2d\u70ed\u70b9\u8bdd\u9898\u68c0\u6d4b\u4e0e\u4f20\u64ad\u5206\u6790\u7814\u7a76","funder_award_id":"61370126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2323930268","display_name":null,"funder_award_id":"U1636211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7104496898","display_name":"\u793e\u533a\u95ee\u7b54\u7cfb\u7edf\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61672081","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2105482032","https://openalex.org/W2124807415","https://openalex.org/W2550821151","https://openalex.org/W2552839021","https://openalex.org/W2565639579","https://openalex.org/W2771979424","https://openalex.org/W2885637246","https://openalex.org/W2888520903","https://openalex.org/W2891924676","https://openalex.org/W2897983179","https://openalex.org/W2902292292","https://openalex.org/W2919290281","https://openalex.org/W2962784628","https://openalex.org/W2962931466","https://openalex.org/W2963446712","https://openalex.org/W2963542740","https://openalex.org/W2964045208","https://openalex.org/W2964093309","https://openalex.org/W2964285114","https://openalex.org/W2965575120","https://openalex.org/W2970290486","https://openalex.org/W2970925677","https://openalex.org/W2987548521","https://openalex.org/W3004289335","https://openalex.org/W3015468748","https://openalex.org/W3017454464","https://openalex.org/W3034742481","https://openalex.org/W3034771276","https://openalex.org/W3035390927","https://openalex.org/W3035747971","https://openalex.org/W3093871477","https://openalex.org/W3102816807","https://openalex.org/W3103334733","https://openalex.org/W3115613018","https://openalex.org/W3119175506","https://openalex.org/W3122073869","https://openalex.org/W3127825258","https://openalex.org/W3155457266","https://openalex.org/W3162226363","https://openalex.org/W3173190788","https://openalex.org/W3174724858","https://openalex.org/W3175746962","https://openalex.org/W3177318507","https://openalex.org/W3188336352","https://openalex.org/W3196326437","https://openalex.org/W6679436768","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6752830811","https://openalex.org/W6754919597","https://openalex.org/W6757585730","https://openalex.org/W6771626834","https://openalex.org/W6772381481","https://openalex.org/W6774776664","https://openalex.org/W6776048684","https://openalex.org/W6783944145","https://openalex.org/W6784072866","https://openalex.org/W6784447870","https://openalex.org/W6787294940","https://openalex.org/W6788927944","https://openalex.org/W6797610904","https://openalex.org/W6803357144"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2775554247","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2949454572","https://openalex.org/W2952599318","https://openalex.org/W2890256614"],"abstract_inverted_index":{"Transformer":[0,21,134],"structure,":[1],"stacked":[2],"by":[3,136],"a":[4,137],"sequence":[5],"of":[6,71,93],"encoder":[7,73,149],"and":[8,36,74,79,99,109,121,125,151],"decoder":[9,75,153],"network":[10],"layers,":[11],"achieves":[12],"significant":[13],"development":[14],"in":[15],"neural":[16],"machine":[17],"translation.":[18],"However,":[19],"vanilla":[20],"mainly":[22],"exploits":[23],"the":[24,28,39,51,91,94,115],"top-layer":[25],"representation,":[26],"assuming":[27],"lower":[29],"layers":[30,150],"provide":[31],"trivial":[32],"or":[33],"redundant":[34],"information":[35],"thus":[37],"ignoring":[38],"bottom-layer":[40],"feature":[41],"that":[42,66,129],"is":[43],"potentially":[44],"valuable.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"propose":[50],"<bold":[52,56],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[53,57,63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</b>":[54],"roup-":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Trans</b>":[58],"former":[59],"model":[60,131],"(":[61],"<sc":[62],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><b>GTrans</b></small>":[64],")":[65],"flexibly":[67],"divides":[68],"multi-layer":[69],"representations":[70],"both":[72],"into":[76],"different":[77],"groups":[78],"then":[80],"fuses":[81],"these":[82],"group":[83],"features":[84],"to":[85,147],"generate":[86],"target":[87],"words.":[88],"To":[89],"corroborate":[90],"effectiveness":[92],"proposed":[95],"method,":[96],"extensive":[97],"experiments":[98,101],"analytic":[100],"are":[102],"conducted":[103],"on":[104],"three":[105,110],"bilingual":[106],"translation":[107,112],"benchmarks":[108],"multilingual":[111],"tasks,":[113],"including":[114],"IWLST-14,":[116],"IWLST-17,":[117],"LDC,":[118],"WMT-14,":[119],"WMT-21":[120],"OPUS-100":[122],"benchmark.":[123],"Experimental":[124],"analytical":[126],"results":[127],"demonstrate":[128],"our":[130],"outperforms":[132],"its":[133],"counterparts":[135],"consistent":[138],"gain.":[139],"Furthermore,":[140],"it":[141],"can":[142],"be":[143],"successfully":[144],"scaled":[145],"up":[146],"60":[148],"36":[152],"layers.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-11-21T00:00:00"}