{"id":"https://openalex.org/W3189675328","doi":"https://doi.org/10.24963/ijcai.2021/712","title":"A Compression-Compilation Framework for On-mobile Real-time BERT Applications","display_name":"A Compression-Compilation Framework for On-mobile Real-time BERT Applications","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3189675328","doi":"https://doi.org/10.24963/ijcai.2021/712","mag":"3189675328"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/712","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/712","pdf_url":"https://www.ijcai.org/proceedings/2021/0712.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0712.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043054935","display_name":"Wei Niu","orcid":"https://orcid.org/0000-0002-2697-7042"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Niu","raw_affiliation_strings":["William & Mary","William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William & Mary","institution_ids":["https://openalex.org/I16285277"]},{"raw_affiliation_string":"William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078971265","display_name":"Zhenglun Kong","orcid":"https://orcid.org/0000-0002-8120-4456"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Zhenglun Kong","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007300551","display_name":"Geng Yuan","orcid":"https://orcid.org/0000-0001-9844-992X"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Geng Yuan","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019027088","display_name":"Weiwen Jiang","orcid":"https://orcid.org/0000-0002-9004-487X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiwen Jiang","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582412","display_name":"Jiexiong Guan","orcid":"https://orcid.org/0000-0001-5274-9169"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiexiong Guan","raw_affiliation_strings":["College of William and Mary","College Of William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of William and Mary","institution_ids":["https://openalex.org/I16285277"]},{"raw_affiliation_string":"College Of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut","University of connecticut"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"University of connecticut","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073885088","display_name":"Pu Zhao","orcid":"https://orcid.org/0000-0001-5018-2859"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Pu Zhao","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321843","display_name":"Sijia Liu","orcid":"https://orcid.org/0000-0003-2817-6991"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sijia Liu","raw_affiliation_strings":["MIT-IBM Watson AI Lab, IBM Research","[MIT-IBM Watson AI Lab, IBM Research]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, IBM Research","institution_ids":[]},{"raw_affiliation_string":"[MIT-IBM Watson AI Lab, IBM Research]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058025888","display_name":"Bin Ren","orcid":"https://orcid.org/0000-0002-4116-5237"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ren","raw_affiliation_strings":["William & Mary","William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William & Mary","institution_ids":["https://openalex.org/I16285277"]},{"raw_affiliation_string":"William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63847132,"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":"5000","last_page":"5003"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9027149677276611},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6641934514045715},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6638178825378418},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6240463256835938},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.6143137812614441},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5494404435157776},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49993371963500977},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4873564839363098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871949017047882},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35842740535736084},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2927107810974121},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.28494954109191895},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17668738961219788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9027149677276611},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6641934514045715},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6638178825378418},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6240463256835938},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6143137812614441},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5494404435157776},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49993371963500977},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4873564839363098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871949017047882},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35842740535736084},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2927107810974121},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28494954109191895},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17668738961219788},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/712","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/712","pdf_url":"https://www.ijcai.org/proceedings/2021/0712.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/712","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/712","pdf_url":"https://www.ijcai.org/proceedings/2021/0712.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3189675328.pdf","grobid_xml":"https://content.openalex.org/works/W3189675328.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1566289585","https://openalex.org/W2074367725","https://openalex.org/W2120575449","https://openalex.org/W2251939518","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2963846996","https://openalex.org/W2964054286","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2978017171","https://openalex.org/W2978670439","https://openalex.org/W3034457371","https://openalex.org/W3148573243","https://openalex.org/W4313908941"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2778498407"],"abstract_inverted_index":{"Transformer-based":[0],"deep":[1],"learning":[2],"models":[3],"have":[4],"increasingly":[5],"demonstrated":[6],"high":[7],"accuracy":[8,60,78],"on":[9,87,116],"many":[10],"natural":[11],"language":[12],"processing":[13],"(NLP)":[14],"tasks.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19],"propose":[20],"a":[21,43],"compression-compilation":[22],"co-design":[23],"framework":[24,41,112],"that":[25,57],"can":[26,51,97,113],"guarantee":[27],"the":[28,53,111],"identified":[29],"model":[30,56],"meets":[31],"both":[32,59],"resource":[33],"and":[34,61,93],"real-time":[35,101],"specifications":[36],"of":[37,84],"mobile":[38,88],"devices.":[39],"Our":[40],"applies":[42],"compiler-aware":[44],"neural":[45],"architecture":[46],"optimization":[47],"method":[48],"(CANAO),":[49],"which":[50],"generate":[52],"optimal":[54],"compressed":[55],"balances":[58],"latency.":[62],"We":[63,80],"are":[64],"able":[65],"to":[66,69],"achieve":[67],"up":[68],"7.8x":[70],"speedup":[71],"compared":[72],"with":[73,75,102],"TensorFlow-Lite":[74],"only":[76],"minor":[77],"loss.":[79],"present":[81],"two":[82],"types":[83],"BERT":[85],"applications":[86],"devices:":[89],"Question":[90],"Answering":[91],"(QA)":[92],"Text":[94],"Generation.":[95],"Both":[96],"be":[98,114],"executed":[99],"in":[100],"latency":[103],"as":[104,106],"low":[105],"45ms.":[107],"Videos":[108],"for":[109],"demonstrating":[110],"found":[115],"https://www.youtube.com/watch?v=_WIRvK_2PZI":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}