{"id":"https://openalex.org/W2965046076","doi":"https://doi.org/10.24963/ijcai.2019/735","title":"Sharing Attention Weights for Fast Transformer","display_name":"Sharing Attention Weights for Fast Transformer","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965046076","doi":"https://doi.org/10.24963/ijcai.2019/735","mag":"2965046076"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/735","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/735","pdf_url":"https://www.ijcai.org/proceedings/2019/0735.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0735.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["NiuTrans Co., Ltd., Shenyang, China","Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Co., Ltd., Shenyang, China","institution_ids":[]},{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083496566","display_name":"Yinqiao Li","orcid":"https://orcid.org/0000-0002-7051-693X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinqiao Li","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370155","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0000-0002-6537-7007"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["NiuTrans Co., Ltd., Shenyang, China","Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Co., Ltd., Shenyang, China","institution_ids":[]},{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Science and Technology, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012126405","display_name":"Tongran Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131870","display_name":"Institute of Psychology, Chinese Academy of Sciences","ror":"https://ror.org/03j7v5j15","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210131870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongran Liu","raw_affiliation_strings":["CAS Key Laboratory of Behavioral Science, Institute of Psychology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Behavioral Science, Institute of Psychology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210131870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5292","last_page":"5298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9969000220298767,"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/nist","display_name":"NIST","score":0.8542423248291016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234608173370361},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.771739661693573},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7057852149009705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6969558596611023},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.659477710723877},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6125588417053223},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4936021566390991},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4592757821083069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4232904016971588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38023650646209717},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3481755256652832},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.22810310125350952},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14158344268798828}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8542423248291016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234608173370361},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.771739661693573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7057852149009705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6969558596611023},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.659477710723877},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6125588417053223},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4936021566390991},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4592757821083069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4232904016971588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38023650646209717},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3481755256652832},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22810310125350952},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14158344268798828},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/735","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/735","pdf_url":"https://www.ijcai.org/proceedings/2019/0735.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/735","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/735","pdf_url":"https://www.ijcai.org/proceedings/2019/0735.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G545337727","display_name":null,"funder_award_id":"61432013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6730576362","display_name":null,"funder_award_id":"N181602013","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6893471174","display_name":null,"funder_award_id":"61876035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8440137829","display_name":"\u9762\u5411\u8d44\u6e90\u7a00\u7f3a\u578b\u8bed\u8a00\u7684\u673a\u5668\u7ffb\u8bd1\u7406\u8bba\u65b9\u6cd5\u53ca\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61732005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965046076.pdf","grobid_xml":"https://content.openalex.org/works/W2965046076.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1902237438","https://openalex.org/W2113104171","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2146950091","https://openalex.org/W2183341477","https://openalex.org/W2525778437","https://openalex.org/W2529089661","https://openalex.org/W2594990650","https://openalex.org/W2613904329","https://openalex.org/W2625113249","https://openalex.org/W2763421725","https://openalex.org/W2767206889","https://openalex.org/W2962944188","https://openalex.org/W2963736842","https://openalex.org/W2963842982","https://openalex.org/W2963928591","https://openalex.org/W2964013027","https://openalex.org/W2964213727","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2058965144","https://openalex.org/W2807901368","https://openalex.org/W2164382479","https://openalex.org/W2133733652","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911"],"abstract_inverted_index":{"Recently,":[0],"the":[1,16,22,31,65,76,84,141,151,157],"Transformer":[2,46],"machine":[3],"translation":[4],"system":[5],"has":[6,122],"shown":[7],"strong":[8],"results":[9,99],"by":[10],"stacking":[11],"attention":[12,36,52,58,158],"layers":[13,62],"on":[14,91,115],"both":[15],"source":[17],"and":[18,50,63,94],"target-language":[19],"sides.":[20],"But":[21],"inference":[23],"of":[24,34,68,106,117,156],"this":[25,41],"model":[26],"is":[27,145],"slow":[28],"due":[29],"to":[30],"heavy":[32],"use":[33,155],"dot-product":[35],"in":[37,60,71,113],"auto-regressive":[38],"decoding.":[39],"In":[40],"paper":[42],"we":[43,56],"speed":[44],"up":[45],"via":[47],"a":[48,72,118,125,134],"fast":[49,128],"lightweight":[51],"model.":[53,86,143],"More":[54],"specifically,":[55],"share":[57],"weights":[59],"adjacent":[61],"enable":[64],"efficient":[66],"re-use":[67],"hidden":[69],"states":[70],"vertical":[73],"manner.":[74],"Moreover,":[75],"sharing":[77],"policy":[78],"can":[79],"be":[80],"jointly":[81],"learned":[82],"with":[83,140,153],"MT":[85],"We":[87],"test":[88],"our":[89,131],"approach":[90,132],"ten":[92],"WMT":[93],"NIST":[95],"OpenMT":[96],"tasks.":[97],"Experimental":[98],"show":[100],"that":[101,121],"it":[102,138],"yields":[103],"an":[104],"average":[105],"1.3X":[107],"speed-up":[108,136],"(with":[109],"almost":[110],"no":[111,154],"decrease":[112],"BLEU)":[114],"top":[116],"state-of-the-art":[119],"implementation":[120],"already":[123],"adopted":[124],"cache":[126],"for":[127],"inference.":[129],"Also,":[130],"obtains":[133],"1.8X":[135],"when":[137],"works":[139],"AAN":[142],"This":[144],"even":[146],"16":[147],"times":[148],"faster":[149],"than":[150],"baseline":[152],"cache.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}