{"id":"https://openalex.org/W4388570696","doi":"https://doi.org/10.1007/s13042-023-01992-6","title":"Fine-tuning pretrained transformer encoders for sequence-to-sequence learning","display_name":"Fine-tuning pretrained transformer encoders for sequence-to-sequence learning","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388570696","doi":"https://doi.org/10.1007/s13042-023-01992-6"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-023-01992-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-023-01992-6","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","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/A5053932343","display_name":"Hangbo Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangbo Bao","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, 92 Xida St., Nangang District, Harbin, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, 92 Xida St., Nangang District, Harbin, 100190, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052630982","display_name":"Dong Li","orcid":"https://orcid.org/0009-0003-4039-434X"},"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":"Li Dong","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370074","display_name":"Wenhui Wang","orcid":"https://orcid.org/0000-0002-3434-5002"},"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":"Wenhui Wang","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072808499","display_name":"Nan Yang","orcid":"https://orcid.org/0000-0002-2621-8927"},"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":"Nan Yang","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775106","display_name":"Songhao Piao","orcid":"https://orcid.org/0000-0003-4351-9112"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songhao Piao","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, 92 Xida St., Nangang District, Harbin, 100190, China"],"raw_orcid":"https://orcid.org/0000-0003-4351-9112","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, 92 Xida St., Nangang District, Harbin, 100190, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","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":["Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Danling St., Haidian District, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101775106"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":3590,"currency":"USD","value_usd":3590},"apc_paid":null,"fwci":2.226,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90115045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"5","first_page":"1711","last_page":"1728"},"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":0.9997000098228455,"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":0.9987999796867371,"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/transformer","display_name":"Transformer","score":0.8515209555625916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309401273727417},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.802359938621521},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7937963008880615},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7774187326431274},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.566810131072998},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5429875254631042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5375188589096069},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.521303117275238},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4245520234107971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3872643709182739},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2126789689064026},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06955656409263611},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057831019163131714}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8515209555625916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309401273727417},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.802359938621521},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7937963008880615},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7774187326431274},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.566810131072998},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5429875254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375188589096069},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.521303117275238},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4245520234107971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3872643709182739},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2126789689064026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06955656409263611},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057831019163131714},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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:10.1007/s13042-023-01992-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-023-01992-6","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2183341477","https://openalex.org/W2250539671","https://openalex.org/W2270070752","https://openalex.org/W2606333299","https://openalex.org/W2606974598","https://openalex.org/W2888482885","https://openalex.org/W2890166583","https://openalex.org/W2922709902","https://openalex.org/W2923014074","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962977247","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2970419734","https://openalex.org/W2970796366","https://openalex.org/W2979826702","https://openalex.org/W2998653236","https://openalex.org/W2998919732","https://openalex.org/W3011411500","https://openalex.org/W3034999214","https://openalex.org/W3035359363","https://openalex.org/W3035390927","https://openalex.org/W3036120435","https://openalex.org/W3098493824","https://openalex.org/W3170214235","https://openalex.org/W3171975879","https://openalex.org/W4214917601","https://openalex.org/W4230872509","https://openalex.org/W4285294723","https://openalex.org/W4378532769","https://openalex.org/W6600165366","https://openalex.org/W6600424091","https://openalex.org/W6600655081","https://openalex.org/W6601141708","https://openalex.org/W6601211009","https://openalex.org/W6605821484","https://openalex.org/W6822365442"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W4392903952","https://openalex.org/W4309877123"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}