{"id":"https://openalex.org/W4320057423","doi":"https://doi.org/10.1145/3573834.3574482","title":"BERT Model Compression With Decoupled Knowledge Distillation And Representation Learning","display_name":"BERT Model Compression With Decoupled Knowledge Distillation And Representation Learning","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4320057423","doi":"https://doi.org/10.1145/3573834.3574482"},"language":"en","primary_location":{"id":"doi:10.1145/3573834.3574482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-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/A5034900998","display_name":"Linna Zhang","orcid":"https://orcid.org/0000-0003-3128-8812"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linna Zhang","raw_affiliation_strings":["School of Information Science and Engineering, University of Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036479222","display_name":"Yuehui Chen","orcid":"https://orcid.org/0000-0002-5265-903X"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehui Chen","raw_affiliation_strings":["School of Information Science and Engineering, University of Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029236521","display_name":"Yi Cao","orcid":"https://orcid.org/0000-0002-1973-5010"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cao","raw_affiliation_strings":["School of Information Science and Engineering, University of Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016306061","display_name":"Yaou Zhao","orcid":"https://orcid.org/0000-0002-4134-2352"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaou Zhao","raw_affiliation_strings":["School of Information Science and Engineering, University of Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034900998"],"corresponding_institution_ids":["https://openalex.org/I34949971"],"apc_list":null,"apc_paid":null,"fwci":0.1379,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57502568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/distillation","display_name":"Distillation","score":0.7461024522781372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845198273658752},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5901722311973572},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.572952389717102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39668700098991394},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11978328227996826},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.05554130673408508},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05154988169670105}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7461024522781372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845198273658752},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5901722311973572},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.572952389717102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39668700098991394},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11978328227996826},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.05554130673408508},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05154988169670105},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573834.3574482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2970454332","https://openalex.org/W3105966348"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Pre-trained":[0],"language":[1,11],"models":[2],"such":[3],"as":[4],"BERT":[5,39],"have":[6],"proven":[7],"essential":[8],"in":[9,26],"natural":[10],"processing(NLP).":[12],"However,":[13],"their":[14],"huge":[15],"number":[16],"of":[17,33,82,94,104,114],"parameters":[18],"and":[19,47,71,86,107],"training":[20],"cost":[21],"make":[22],"them":[23],"very":[24],"limited":[25],"practical":[27],"deployment.":[28],"To":[29],"overcome":[30],"BERT\u2019s":[31],"lack":[32],"computing":[34],"resources,":[35],"we":[36],"propose":[37],"a":[38,55],"compression":[40],"method":[41],"by":[42],"applying":[43],"decoupled":[44],"knowledge":[45,59,69,74],"distillation":[46,60,64],"representation":[48],"learning,":[49],"compressing":[50],"the":[51,62,79,87,91,95,115],"large":[52,116],"model(teacher)":[53],"into":[54,66],"lightweight":[56],"network(student).":[57],"Decoupled":[58],"divides":[61],"classical":[63],"loss":[65],"target":[67],"related":[68,73],"distillation(TRKD)":[70],"non-target":[72],"distillation(NRKD).":[75],"Representation":[76],"learning":[77],"pools":[78],"Transformer":[80],"output":[81],"each":[83],"two":[84],"layers,":[85],"student":[88],"network":[89],"learns":[90],"intermediate":[92],"features":[93],"teacher":[96],"network.":[97],"It":[98],"has":[99],"better":[100],"results":[101],"on":[102],"tasks":[103],"Sentiment":[105],"Classification":[106],"Paraphrase":[108],"Similarity":[109],"Matching,":[110],"retaining":[111],"98.9%":[112],"performance":[113],"model.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}