{"id":"https://openalex.org/W3006963874","doi":"https://doi.org/10.1007/s11390-021-1119-0","title":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","display_name":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W3006963874","doi":"https://doi.org/10.1007/s11390-021-1119-0","mag":"3006963874"},"language":"en","primary_location":{"id":"doi:10.1007/s11390-021-1119-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11390-021-1119-0","pdf_url":null,"source":{"id":"https://openalex.org/S161516442","display_name":"Journal of Computer Science and Technology","issn_l":"1000-9000","issn":["1000-9000","1860-4749"],"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":"Journal of Computer Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.10345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054178885","display_name":"Yige Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Ge Xu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 200433, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xi-Peng Qiu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 200433, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113660867","display_name":"Li-Gao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Gao Zhou","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Hangzhou, 310052, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Hangzhou, 310052, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan-Jing Huang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 200433, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044665993"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":3.5583,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.93917966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"38","issue":"4","first_page":"853","last_page":"866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9894999861717224,"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":0.8226519823074341},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8022902011871338},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7858073711395264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5681160688400269},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5185540318489075},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5081634521484375},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48203837871551514},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.460203617811203},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.44353121519088745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06616365909576416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226519823074341},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8022902011871338},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7858073711395264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681160688400269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5185540318489075},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5081634521484375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48203837871551514},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.460203617811203},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.44353121519088745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06616365909576416},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11390-021-1119-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11390-021-1119-0","pdf_url":null,"source":{"id":"https://openalex.org/S161516442","display_name":"Journal of Computer Science and Technology","issn_l":"1000-9000","issn":["1000-9000","1860-4749"],"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":"Journal of Computer Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.10345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.10345","pdf_url":"https://arxiv.org/pdf/2002.10345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2002.10345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.10345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.10345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.10345","pdf_url":"https://arxiv.org/pdf/2002.10345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1821462560","https://openalex.org/W1840435438","https://openalex.org/W2086161653","https://openalex.org/W2109553965","https://openalex.org/W2113459411","https://openalex.org/W2251939518","https://openalex.org/W2578980197","https://openalex.org/W2592691248","https://openalex.org/W2626778328","https://openalex.org/W2739351760","https://openalex.org/W2784121710","https://openalex.org/W2786928559","https://openalex.org/W2911300548","https://openalex.org/W2913946806","https://openalex.org/W2914526845","https://openalex.org/W2921848006","https://openalex.org/W2923014074","https://openalex.org/W2937297214","https://openalex.org/W2944869267","https://openalex.org/W2945260553","https://openalex.org/W2945824677","https://openalex.org/W2950813464","https://openalex.org/W2951970475","https://openalex.org/W2953084091","https://openalex.org/W2963026768","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2964001908","https://openalex.org/W2965373594","https://openalex.org/W2970352191","https://openalex.org/W2970454332","https://openalex.org/W2970597249","https://openalex.org/W2978017171","https://openalex.org/W2978670439","https://openalex.org/W2980708516","https://openalex.org/W3008374555","https://openalex.org/W3011574394","https://openalex.org/W3014568172","https://openalex.org/W3034457371","https://openalex.org/W3035030897","https://openalex.org/W3088409176","https://openalex.org/W3104033643","https://openalex.org/W3105966348","https://openalex.org/W3149839747","https://openalex.org/W6676984168","https://openalex.org/W6687681856","https://openalex.org/W6739901393","https://openalex.org/W6740801417","https://openalex.org/W6748554570","https://openalex.org/W6759579507"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W3154646238","https://openalex.org/W4309877123"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":14}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2020-03-06T00:00:00"}