{"id":"https://openalex.org/W4390548173","doi":"https://doi.org/10.1145/3632410.3632451","title":"NanoBERT: An Extremely Compact Language Model","display_name":"NanoBERT: An Extremely Compact Language Model","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390548173","doi":"https://doi.org/10.1145/3632410.3632451"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632451","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632410.3632451","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632410.3632451","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3632410.3632451","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073512569","display_name":"Krishanu Maity","orcid":"https://orcid.org/0000-0002-9542-9250"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Krishanu Maity","raw_affiliation_strings":["Samsung R&D Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-9542-9250","affiliations":[{"raw_affiliation_string":"Samsung R&D Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013704954","display_name":"Amit Chaulwar","orcid":"https://orcid.org/0000-0003-3466-4027"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Tulsidas Chaulwar","raw_affiliation_strings":["Samsung R&D Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0003-3466-4027","affiliations":[{"raw_affiliation_string":"Samsung R&D Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028145573","display_name":"Vanraj Vala","orcid":"https://orcid.org/0009-0001-1182-4529"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vanraj Vala","raw_affiliation_strings":["Samsung R&D Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0001-1182-4529","affiliations":[{"raw_affiliation_string":"Samsung R&D Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065336819","display_name":"Ravi Sankar Guntur","orcid":"https://orcid.org/0009-0007-0157-5091"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Sankar Guntur","raw_affiliation_strings":["Samsung R&D Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0007-0157-5091","affiliations":[{"raw_affiliation_string":"Samsung R&D Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073512569"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":1.3245,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82022036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"342","last_page":"349"},"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":0.9973999857902527,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.871660590171814},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7317677140235901},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6733282208442688},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6480712294578552},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6392116546630859},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5519629120826721},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5014095306396484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45876163244247437},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43872392177581787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3291124701499939},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18581166863441467},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10085436701774597},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09996318817138672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871660590171814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7317677140235901},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6733282208442688},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6480712294578552},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6392116546630859},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5519629120826721},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5014095306396484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45876163244247437},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43872392177581787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3291124701499939},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18581166863441467},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10085436701774597},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09996318817138672},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632451","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632410.3632451","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632410.3632451","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3632410.3632451","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632410.3632451","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632410.3632451","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390548173.pdf","grobid_xml":"https://content.openalex.org/works/W4390548173.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2524428287","https://openalex.org/W2747579829","https://openalex.org/W2946794439","https://openalex.org/W3099559063","https://openalex.org/W3137762660","https://openalex.org/W3173380736","https://openalex.org/W4220785642","https://openalex.org/W4252110927","https://openalex.org/W4324057834"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W2997152889","https://openalex.org/W4386245174","https://openalex.org/W4200132709"],"abstract_inverted_index":{"Language":[0],"model":[1,79,114],"pre-training,":[2],"such":[3,21,103],"as":[4,22,104],"in":[5,13,61,128],"BERT":[6,78,93],"model,":[7,63],"has":[8],"led":[9],"to":[10,30,52],"significant":[11],"improvements":[12],"natural":[14],"language":[15,32],"processing":[16],"tasks.":[17],"Although":[18],"many":[19],"approaches":[20],"quantization,":[23],"knowledge":[24],"distillation,":[25],"etc.":[26,110],"have":[27],"been":[28],"proposed":[29],"compress":[31],"models,":[33],"they":[34],"are":[35],"still":[36],"not":[37],"suitable":[38],"for":[39,125],"deployment":[40],"on":[41,99],"resource-constrained":[42],"edge":[43],"devices":[44],"like":[45],"mobiles.":[46],"In":[47],"this":[48,71,113],"work,":[49],"we":[50,73],"propose":[51],"replace":[53],"the":[54],"token":[55],"embedding":[56],"matrix,":[57],"an":[58],"expensive":[59],"layer":[60],"Transformer":[62],"with":[64,118],"trainable":[65],"rank":[66],"decomposition":[67],"matrices.":[68],"Building":[69],"upon":[70],"approach,":[72],"introduce":[74],"NanoBERT,":[75],"a":[76],"lightweight":[77],"that":[80],"is":[81],"nearly":[82],"17":[83],"\u00d7":[84],"smaller":[85],"than":[86],"BERT-Tiny":[87],"(the":[88],"smallest":[89],"open":[90],"source":[91],"pre-trained":[92],"model),":[94],"yet":[95],"attains":[96],"comparable":[97],"performance":[98],"various":[100],"NLP":[101],"tasks":[102],"text":[105],"classification,":[106],"named":[107,123],"entity":[108],"recognition,":[109],"We":[111],"extend":[112],"by":[115],"combining":[116],"it":[117],"parameter":[119],"efficient":[120],"fine-tuning":[121],"technique,":[122],"LoRA,":[124],"further":[126],"compression":[127],"multi-task":[129],"scenarios.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}