{"id":"https://openalex.org/W4412944865","doi":"https://doi.org/10.18653/v1/2025.acl-long.1067","title":"Maximizing the Effectiveness of Larger BERT Models for Compression","display_name":"Maximizing the Effectiveness of Larger BERT Models for Compression","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944865","doi":"https://doi.org/10.18653/v1/2025.acl-long.1067"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1067","pdf_url":"https://aclanthology.org/2025.acl-long.1067.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1067.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119204388","display_name":"Wen-Shu Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Shu Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103179805","display_name":"Shao-Wei Lu","orcid":"https://orcid.org/0000-0002-5182-8962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110723147","display_name":"Shuyuan Xing","orcid":"https://orcid.org/0009-0001-7677-6011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangyu Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057076521","display_name":"Xin-Chun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin-Chun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119204389","display_name":"De-Chuan Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De-Chuan Zhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19656804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21975","last_page":"21990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.25130000710487366,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.25130000710487366,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.22130000591278076,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5912846922874451},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5407180786132812},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13912564516067505},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.12008023262023926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5912846922874451},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5407180786132812},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13912564516067505},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.12008023262023926}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1067","pdf_url":"https://aclanthology.org/2025.acl-long.1067.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1067","pdf_url":"https://aclanthology.org/2025.acl-long.1067.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1728705413","display_name":null,"funder_award_id":"2022ZD0114805","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944865.pdf","grobid_xml":"https://content.openalex.org/works/W4412944865.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,85],"(KD)":[2],"is":[3],"a":[4,12,18,24,33,44],"widely":[5],"used":[6],"approach":[7,86],"for":[8,57],"BERT":[9,14,35,59,102],"compression,":[10],"where":[11],"larger":[13,34,58,77,101],"model":[15],"serves":[16],"as":[17],"teacher":[19],"to":[20,23,70,104],"transfer":[21],"knowledge":[22,90,106],"smaller":[25,45],"student":[26],"model.Prior":[27],"works":[28],"have":[29],"found":[30],"that":[31,66,87],"distilling":[32],"with":[36],"superior":[37],"performance":[38,42],"may":[39],"degrade":[40],"student's":[41],"than":[43],"BERT.In":[46],"this":[47],"paper,":[48],"we":[49,64,81],"investigate":[50],"the":[51,73,94],"limitations":[52],"of":[53,76,96],"existing":[54],"KD":[55],"methods":[56,68],"models.Through":[60],"Canonical":[61],"Correlation":[62],"Analysis,":[63],"identify":[65],"these":[67],"fail":[69],"fully":[71],"exploit":[72],"potential":[74],"advantages":[75],"teachers.To":[78],"address":[79],"this,":[80],"propose":[82],"an":[83],"improved":[84],"effectively":[88],"enhances":[89],"transfer.Comprehensive":[91],"experiments":[92],"demonstrate":[93],"effectiveness":[95],"our":[97],"method":[98],"in":[99],"enabling":[100],"models":[103],"distill":[105],"more":[107],"efficiently.":[108]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
