{"id":"https://openalex.org/W45102278","doi":"https://doi.org/10.21437/icslp.2000-490","title":"Language model size reduction by pruning and clustering","display_name":"Language model size reduction by pruning and clustering","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W45102278","doi":"https://doi.org/10.21437/icslp.2000-490","mag":"45102278"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110237290","display_name":"Joshua Goodman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua Goodman","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.8098,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.89656508,"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":"vol. 3, 110","last_page":"113"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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/perplexity","display_name":"Perplexity","score":0.9801425933837891},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8575324416160583},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6971343159675598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.659259021282196},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6264364719390869},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4930567443370819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49270132184028625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3275042474269867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2629961371421814}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9801425933837891},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8575324416160583},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6971343159675598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659259021282196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6264364719390869},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4930567443370819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49270132184028625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3275042474269867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2629961371421814},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2000-490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.7723","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.7723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.microsoft.com/china/research/group/../downloads/g-nlps/NLPSP/n13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1797288984","https://openalex.org/W1903115690","https://openalex.org/W2121227244","https://openalex.org/W2145826596","https://openalex.org/W2441154163","https://openalex.org/W4302312245"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"Several":[0],"techniques":[1,30,55],"are":[2,100,115],"known":[3],"for":[4],"reducing":[5],"the":[6,65,91,104,121],"size":[7],"of":[8,28,79],"language":[9],"models,":[10,106],"including":[11],"count":[12,48],"cutoffs":[13],"[1],":[14],"Weighted":[15,42],"Difference":[16,43],"pruning":[17,20,40,46,62],"[2],":[18],"Stolcke":[19,45,61,88],"[3],":[21],"and":[22,31,44],"clustering":[23,54],"[4].":[24],"We":[25,50],"compare":[26],"all":[27],"these":[29],"show":[32,52],"some":[33],"surprising":[34],"results.":[35],"For":[36],"instance,":[37],"at":[38,68,90],"low":[39],"thresholds,":[41],"underperform":[47],"cutoffs.":[49],"then":[51],"novel":[53],"that":[56,99,114],"can":[57,75,109],"be":[58,76,110],"combined":[59],"with":[60,87,120],"to":[63,112],"produce":[64],"smallest":[66],"models":[67,74,85,98,113,119],"a":[69,77],"given":[70],"perplexity.":[71,93,123],"The":[72,94],"resulting":[73],"factor":[78],"three":[80],"or":[81],"more":[82],"smaller":[83,116],"than":[84,103,117],"pruned":[86,111],"pruning,":[89],"same":[92,122],"technique":[95],"creates":[96],"clustered":[97],"often":[101],"larger":[102],"unclustered":[105,118],"but":[107],"which":[108]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}