{"id":"https://openalex.org/W2963928591","doi":"https://doi.org/10.1609/aaai.v33i01.33016292","title":"Recurrent Stacking of Layers for Compact Neural Machine Translation Models","display_name":"Recurrent Stacking of Layers for Compact Neural Machine Translation Models","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963928591","doi":"https://doi.org/10.1609/aaai.v33i01.33016292","mag":"2963928591"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016292","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016292","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33016292","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101988321","display_name":"Atsushi Fujita","orcid":"https://orcid.org/0000-0003-3799-8428"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"6292","last_page":"6299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9922999739646912,"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":0.9503999948501587,"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/encoder","display_name":"Encoder","score":0.8219406604766846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032243251800537},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.784083902835846},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7520101070404053},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6842617392539978},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.6518121361732483},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6266334652900696},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5898949503898621},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5005936622619629},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48034512996673584},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4733167886734009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.459044873714447},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4191305637359619},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34012848138809204},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3373536169528961},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08359912037849426},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.05624660849571228}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8219406604766846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032243251800537},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.784083902835846},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7520101070404053},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6842617392539978},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.6518121361732483},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6266334652900696},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5898949503898621},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5005936622619629},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48034512996673584},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4733167886734009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.459044873714447},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4191305637359619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34012848138809204},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3373536169528961},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08359912037849426},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.05624660849571228},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33016292","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016292","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4590","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4590","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4590/4468","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016292","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016292","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1816313093","https://openalex.org/W1821462560","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2284660317","https://openalex.org/W2550821151","https://openalex.org/W2573761686","https://openalex.org/W2576482813","https://openalex.org/W2587694128","https://openalex.org/W2595715041","https://openalex.org/W2799001369","https://openalex.org/W2806888788","https://openalex.org/W2866343820","https://openalex.org/W2887516053","https://openalex.org/W2962784628","https://openalex.org/W2963216553","https://openalex.org/W2964213727","https://openalex.org/W4298159529","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6666761814","https://openalex.org/W6679436768","https://openalex.org/W6732150968","https://openalex.org/W6732265328","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W4376641153","https://openalex.org/W2050788868","https://openalex.org/W4250391473","https://openalex.org/W4302292679","https://openalex.org/W2956222435","https://openalex.org/W4241625287","https://openalex.org/W2184170131","https://openalex.org/W2330571978","https://openalex.org/W2221419418"],"abstract_inverted_index":{"In":[0,49],"encoder-decoder":[1],"based":[2],"sequence-to-sequence":[3,66],"modeling,":[4],"the":[5,21,26,33,45,94,150,158,175,184,187],"most":[6],"common":[7],"practice":[8],"is":[9],"to":[10,40,54,62,193],"stack":[11],"a":[12,41,63,86,98,103,115,131],"number":[13,46],"of":[14,28,47,88,97,114,152,160,177,196],"recurrent,":[15],"convolutional,":[16],"or":[17],"feed-forward":[18],"layers":[19,59,155,166],"in":[20,44,191],"encoder":[22,188],"and":[23,167,189],"decoder.":[24],"While":[25],"addition":[27,192],"each":[29],"new":[30],"layer":[31],"improves":[32],"sequence":[34],"generation":[35],"quality,":[36],"this":[37,50],"also":[38,123],"leads":[39],"significant":[42],"increase":[43],"parameters.":[48],"paper,":[51],"we":[52,173,181],"propose":[53],"share":[55,182],"parameters":[56,185],"across":[57],"all":[58],"thereby":[60],"leading":[61],"recurrently":[64,101,153,164],"stacked":[65,154,165],"model.":[67],"We":[68,90,122,147],"report":[69],"on":[70,75],"an":[71],"extensive":[72],"case":[73],"study":[74],"neural":[76],"machine":[77],"translation":[78,95],"(NMT)":[79],"using":[80],"our":[81,126],"proposed":[82],"method,":[83],"experimenting":[84],"with":[85,141],"variety":[87],"datasets.":[89],"empirically":[91],"show":[92,124],"that":[93,100,113,117,162,169],"quality":[96],"model":[99,116],"stacks":[102,118],"single-layer":[104],"6":[105,119],"times,":[106],"despite":[107],"its":[108],"significantly":[109],"fewer":[110],"parameters,":[111],"approaches":[112],"different":[120],"layers.":[121,197],"how":[125],"method":[127],"can":[128],"benefit":[129],"from":[130],"prevalent":[132],"way":[133],"for":[134],"improving":[135],"NMT,":[136],"i.e.,":[137],"extending":[138],"training":[139],"data":[140],"pseudo-parallel":[142],"corpora":[143],"generated":[144],"by":[145,156],"back-translation.":[146],"then":[148],"analyze":[149],"effects":[151],"visualizing":[157],"attentions":[159],"models":[161,168],"use":[163],"do":[170],"not.":[171],"Finally,":[172],"explore":[174],"limits":[176],"parameter":[178],"sharing":[179],"where":[180],"even":[183],"between":[186],"decoder":[190],"recurrent":[194],"stacking":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}