{"id":"https://openalex.org/W3128362158","doi":"https://doi.org/10.1145/3443279.3443302","title":"Compressed-Transformer","display_name":"Compressed-Transformer","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3128362158","doi":"https://doi.org/10.1145/3443279.3443302","mag":"3128362158"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443302","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 Natural Language Processing and Information Retrieval","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/A5089139497","display_name":"Yuan Chen","orcid":"https://orcid.org/0000-0002-2301-4195"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan, Chen","raw_affiliation_strings":["School of Data and Computer Science Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075012459","display_name":"Rong Pan","orcid":"https://orcid.org/0000-0001-5171-8248"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Rong","raw_affiliation_strings":["School of Data and Computer Science Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089139497"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20093256,"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":"131","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9961000084877014,"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":0.9922999739646912,"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":0.7916265726089478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694648027420044},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5615381598472595},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4966662526130676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4340388774871826},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.42340147495269775},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2818329930305481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13047972321510315},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11320480704307556}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7916265726089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694648027420044},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5615381598472595},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4966662526130676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4340388774871826},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.42340147495269775},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2818329930305481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13047972321510315},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11320480704307556},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3443279.3443302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443302","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 Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1753482797","https://openalex.org/W2024165284","https://openalex.org/W2133564696","https://openalex.org/W2294370754","https://openalex.org/W2345720230","https://openalex.org/W2561238782","https://openalex.org/W2572474373","https://openalex.org/W2924902521","https://openalex.org/W2952899695","https://openalex.org/W2970454332","https://openalex.org/W2970565456","https://openalex.org/W2972324944","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W2978832950","https://openalex.org/W2984898826","https://openalex.org/W3023166997","https://openalex.org/W3035317912","https://openalex.org/W3105966348","https://openalex.org/W4248902798","https://openalex.org/W6638523607"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W3098873988","https://openalex.org/W2952599318","https://openalex.org/W2890256614","https://openalex.org/W4206178588","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Recently,":[0],"Transformer":[1,16,42,56,90],"has":[2],"achieved":[3],"state-of-the-art":[4],"performance":[5],"in":[6,15,81],"neural":[7],"machine":[8],"translation.":[9],"However,":[10],"the":[11,59,77,114,134,142,157,161,178],"number":[12,60,135],"of":[13,41,61,99,109,136,149,156],"parameters":[14,50,62,137],"is":[17,138,164],"so":[18],"large":[19],"that":[20,118,155],"it":[21],"needs":[22],"to":[23,54,85,92],"be":[24,64],"compressed":[25,39,120],"before":[26],"deployed":[27],"and":[28,51,104,113,160],"executed":[29],"on":[30,168,173],"resource-restricted":[31],"devices.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"propose":[37],"a":[38,72,105],"version":[40],"called":[43],"Compressed-Transformer.":[44],"We":[45,70],"introduce":[46],"two":[47],"techniques,":[48],"factorizing":[49],"block":[52],"reduction,":[53],"compress":[55],"model.":[57,131],"Consequently,":[58],"can":[63,145],"reduced":[65,139],"by":[66,140,166],"more":[67],"than":[68,128,154],"50%.":[69],"exploit":[71],"stage-wise":[73],"distillation":[74,83],"strategy":[75],"with":[76],"temperature":[78],"dynamically":[79],"adjusted":[80],"knowledge":[82,87],"practice":[84],"transfer":[86],"from":[88],"base":[89],"(teacher)":[91],"Compressed-Transformer":[93],"(student).":[94],"A":[95],"Chinese-to-English":[96],"(Zh~En)":[97],"dataset":[98,108,175],"United":[100],"Nations":[101],"Parallel":[102],"Corpus":[103],"German-to-English":[106],"(De~En)":[107],"Multi30K":[110],"are":[111],"used,":[112],"experimental":[115],"results":[116],"show":[117],"our":[119],"model":[121,144],"achieves":[122],"BLEU":[123,147],"score":[124,148],"only":[125,151],"slightly":[126],"lower":[127,153],"uncompressed":[129],"teacher":[130,158],"Specially,":[132],"when":[133],"59.3%,":[141],"student":[143],"achieve":[146,177],"40.69,":[150],"1.64":[152],"model,":[159],"inference":[162],"speed":[163],"improved":[165],"17%":[167],"Zh~En":[169],"dataset.":[170],"The":[171],"experiments":[172],"De~En":[174],"also":[176],"similar":[179],"results.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}