{"id":"https://openalex.org/W3016230677","doi":"https://doi.org/10.1109/icassp40776.2020.9053483","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","display_name":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016230677","doi":"https://doi.org/10.1109/icassp40776.2020.9053483","mag":"3016230677"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5011790590","display_name":"Junhao Xu","orcid":"https://orcid.org/0000-0002-9650-0290"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junhao Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035435409","display_name":"Chen Xie","orcid":"https://orcid.org/0000-0002-9225-3106"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045355404","display_name":"Shoukang Hu","orcid":"https://orcid.org/0000-0002-3345-6923"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoukang Hu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011790590"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83192539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7939","last_page":"7943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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/T10320","display_name":"Neural Networks and Applications","score":0.9934999942779541,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9829999804496765,"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/quantization","display_name":"Quantization (signal processing)","score":0.85693359375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830554246902466},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.6812365651130676},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6371743083000183},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.589210033416748},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45986247062683105},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43434977531433105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35852348804473877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3112870156764984}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.85693359375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830554246902466},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.6812365651130676},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6371743083000183},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.589210033416748},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45986247062683105},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43434977531433105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35852348804473877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3112870156764984},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W101286142","https://openalex.org/W587794757","https://openalex.org/W1519983590","https://openalex.org/W1701967867","https://openalex.org/W1724438581","https://openalex.org/W1821462560","https://openalex.org/W1825672851","https://openalex.org/W1902934009","https://openalex.org/W1935978687","https://openalex.org/W1996901117","https://openalex.org/W2058641082","https://openalex.org/W2076094076","https://openalex.org/W2119144962","https://openalex.org/W2125031621","https://openalex.org/W2136939460","https://openalex.org/W2144790469","https://openalex.org/W2161758346","https://openalex.org/W2164278908","https://openalex.org/W2172166488","https://openalex.org/W2182629226","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2402268235","https://openalex.org/W2405920868","https://openalex.org/W2508418541","https://openalex.org/W2524428287","https://openalex.org/W2560017826","https://openalex.org/W2739789140","https://openalex.org/W2786951478","https://openalex.org/W2803431233","https://openalex.org/W2886512927","https://openalex.org/W2888930363","https://openalex.org/W2899771611","https://openalex.org/W2949964376","https://openalex.org/W2962833442","https://openalex.org/W2963000224","https://openalex.org/W2963048316","https://openalex.org/W2963114950","https://openalex.org/W2963225922","https://openalex.org/W2963318827","https://openalex.org/W2963424132","https://openalex.org/W2963674932","https://openalex.org/W2963736842","https://openalex.org/W2964299589","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4292363360","https://openalex.org/W4294371482","https://openalex.org/W6604085896","https://openalex.org/W6617368339","https://openalex.org/W6637687001","https://openalex.org/W6637709462","https://openalex.org/W6638523607","https://openalex.org/W6638839971","https://openalex.org/W6639703010","https://openalex.org/W6640289440","https://openalex.org/W6649495467","https://openalex.org/W6669713995","https://openalex.org/W6677580257","https://openalex.org/W6678885109","https://openalex.org/W6679667936","https://openalex.org/W6680230698","https://openalex.org/W6680532216","https://openalex.org/W6684089856","https://openalex.org/W6685405536","https://openalex.org/W6685891324","https://openalex.org/W6686067075","https://openalex.org/W6698200048","https://openalex.org/W6700264148","https://openalex.org/W6713098461","https://openalex.org/W6714058667","https://openalex.org/W6725543821","https://openalex.org/W6727208969","https://openalex.org/W6730047919","https://openalex.org/W6748131973","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2740662036","https://openalex.org/W3142119062","https://openalex.org/W2964047924","https://openalex.org/W3150294986","https://openalex.org/W4299838440","https://openalex.org/W2962832505","https://openalex.org/W2743945814","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"The":[0],"high":[1],"memory":[2],"consumption":[3],"and":[4,94,109],"computational":[5],"costs":[6],"of":[7,32,48,79,123,136],"Recurrent":[8],"neural":[9,25,50],"network":[10,26],"language":[11],"models":[12],"(RNNLMs)":[13],"limit":[14],"their":[15],"wider":[16],"application":[17],"on":[18,103],"resource":[19],"constrained":[20],"devices.":[21],"In":[22],"recent":[23],"years,":[24],"quantization":[27,100,116,147],"techniques":[28],"that":[29],"are":[30,41],"capable":[31],"producing":[33],"extremely":[34],"low-bit":[35,99],"compression,":[36],"for":[37],"example,":[38],"binarized":[39,145],"RNNLMs,":[40],"gaining":[42],"increasing":[43],"research":[44],"interests.":[45],"Directly":[46],"training":[47,58,141],"quantized":[49,56,71],"networks":[51],"is":[52],"difficult.":[53],"By":[54],"formulating":[55],"RNNLMs":[57,72],"as":[59],"an":[60],"optimization":[61],"problem,":[62],"this":[63],"paper":[64],"presents":[65],"a":[66,118],"novel":[67],"method":[68,83],"to":[69,125],"train":[70],"from":[73],"scratch":[74],"using":[75,97],"alternating":[76],"direction":[77],"methods":[78],"multipliers":[80],"(ADMM).":[81],"This":[82],"can":[84],"also":[85,149],"flexibly":[86],"adjust":[87],"the":[88,91,113,129,143],"trade-off":[89],"between":[90],"compression":[92,121],"rate":[93],"model":[95,119,140],"performance":[96],"tied":[98],"tables.":[101],"Experiments":[102],"two":[104],"tasks:":[105],"Penn":[106],"Treebank":[107],"(PTB),":[108],"Switchboard":[110],"(SWBD)":[111],"suggest":[112],"proposed":[114],"ADMM":[115],"achieved":[117],"size":[120],"factor":[122],"up":[124],"31":[126],"times":[127,138],"over":[128,142],"full":[130],"precision":[131],"baseline":[132,144],"RNNLMs.":[133],"Faster":[134],"convergence":[135],"5":[137],"in":[139],"RNNLM":[146],"was":[148],"obtained.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}