{"id":"https://openalex.org/W2130917146","doi":"https://doi.org/10.1109/asru.2009.5373380","title":"Scaling shrinkage-based language models","display_name":"Scaling shrinkage-based language models","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2130917146","doi":"https://doi.org/10.1109/asru.2009.5373380","mag":"2130917146"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5090361189","display_name":"Stanley F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stanley F. Chen","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019973376","display_name":"Lidia Mangu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lidia Mangu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruhi Sarikaya","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090361189"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":9.0326,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97899254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"299","last_page":"304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9986000061035156,"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/language-model","display_name":"Language model","score":0.8012160658836365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387738227844238},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5698671340942383},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5689054131507874},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5373702049255371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5329362750053406},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.509088933467865},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4479045569896698},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44439712166786194},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.4271640479564667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4137556552886963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4046246111392975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16741156578063965}],"concepts":[{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8012160658836365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387738227844238},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5698671340942383},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5689054131507874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5373702049255371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329362750053406},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.509088933467865},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4479045569896698},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44439712166786194},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4271640479564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4137556552886963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4046246111392975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16741156578063965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5373380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.8097","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.8097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/~stanchen/papers/d033l1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W14331692","https://openalex.org/W1481113913","https://openalex.org/W1550982044","https://openalex.org/W1718044877","https://openalex.org/W1797288984","https://openalex.org/W1887099548","https://openalex.org/W1974515274","https://openalex.org/W1996903695","https://openalex.org/W2001792610","https://openalex.org/W2049901611","https://openalex.org/W2050971845","https://openalex.org/W2072223048","https://openalex.org/W2076467305","https://openalex.org/W2097003869","https://openalex.org/W2098318492","https://openalex.org/W2101105183","https://openalex.org/W2109664771","https://openalex.org/W2121227244","https://openalex.org/W2127095586","https://openalex.org/W2130917146","https://openalex.org/W2142340904","https://openalex.org/W2147467930","https://openalex.org/W2153653739","https://openalex.org/W2154124206","https://openalex.org/W2156985047","https://openalex.org/W2157112198","https://openalex.org/W2158195707","https://openalex.org/W2160842254","https://openalex.org/W2161347627","https://openalex.org/W2161513525","https://openalex.org/W6643925177","https://openalex.org/W6674504384","https://openalex.org/W6678277124","https://openalex.org/W6683603519"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2043093291","https://openalex.org/W2101155126","https://openalex.org/W2363545964"],"abstract_inverted_index":{"In":[0,57],"we":[1,60,78,108,135],"show":[2,149],"that":[3,41,91,150],"a":[4,95,140],"novel":[5],"class-based":[6],"language":[7,51,159],"model,":[8],"Model":[9,116,151],"M,":[10],"and":[11,73,118,148,168],"the":[12,39,43],"method":[13],"of":[14,27,33,45,142],"regularized":[15],"minimum":[16],"discrimination":[17],"information":[18],"(rMDI)":[19],"models":[20,120,160],"outperform":[21],"comparable":[22],"methods":[23,35,111,138],"on":[24,69,74,83,121,131,139],"moderate":[25],"amounts":[26],"Wall":[28],"Street":[29],"Journal":[30],"data.":[31],"Both":[32],"these":[34,63,137],"are":[36],"motivated":[37],"by":[38,89],"observation":[40],"shrinking":[42],"sum":[44],"parameter":[46],"magnitudes":[47],"in":[48,164],"an":[49],"exponential":[50],"model":[52,98],"tends":[53],"to":[54,94,100,124],"improve":[55],"performance.":[56],"this":[58],"paper,":[59],"investigate":[61],"whether":[62],"shrinkage-based":[64],"techniques":[65,127],"also":[66],"perform":[67],"well":[68],"larger":[70],"training":[71,103],"sets":[72,86],"other":[75],"domains.":[76,133],"First,":[77],"explain":[79],"why":[80],"good":[81],"performance":[82],"large":[84,132],"data":[85],"is":[87],"uncertain,":[88],"showing":[90],"gains":[92,156],"relative":[93],"baseline":[96],"n-gram":[97],"tend":[99],"decrease":[101],"as":[102],"set":[104],"size":[105],"increases.":[106],"Next,":[107],"evaluate":[109],"several":[110,146],"for":[112,161],"data/model":[113],"combination":[114],"with":[115],"M":[117,152],"rMDI":[119],"limited-scale":[122],"domains,":[123],"uncover":[125],"which":[126],"should":[128],"work":[129],"best":[130],"Finally,":[134],"apply":[136],"variety":[141],"medium-to-large-scale":[143],"domains":[144],"covering":[145],"languages,":[147],"consistently":[153],"provides":[154],"significant":[155],"over":[157],"existing":[158],"state-of-the-art":[162],"systems":[163],"both":[165],"speech":[166],"recognition":[167],"machine":[169],"translation.":[170]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}