{"id":"https://openalex.org/W1965154800","doi":"https://doi.org/10.1109/asru.2011.6163930","title":"Strategies for training large scale neural network language models","display_name":"Strategies for training large scale neural network language models","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1965154800","doi":"https://doi.org/10.1109/asru.2011.6163930","mag":"1965154800"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000621526","display_name":"Anoop Deoras","orcid":"https://orcid.org/0009-0007-4566-8767"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anoop Deoras","raw_affiliation_strings":["HLT-COE, CLSP, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HLT-COE, CLSP, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"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":"Daniel Povey","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":514,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9994999766349792,"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":0.9990000128746033,"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":0.852056086063385},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7771903872489929},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6463667154312134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5599250793457031},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.541507363319397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5342981219291687},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5190330743789673},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5016589164733887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4731396734714508},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4722670316696167},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4483387768268585},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.43989044427871704},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4354203939437866},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4337519109249115},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40388917922973633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852056086063385},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7771903872489929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6463667154312134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5599250793457031},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.541507363319397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342981219291687},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5190330743789673},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5016589164733887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4731396734714508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722670316696167},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4483387768268585},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.43989044427871704},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4354203939437866},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4337519109249115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40388917922973633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2011.6163930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W115367774","https://openalex.org/W179707045","https://openalex.org/W179875071","https://openalex.org/W1508567213","https://openalex.org/W1970689298","https://openalex.org/W1996903695","https://openalex.org/W2050971845","https://openalex.org/W2100714283","https://openalex.org/W2105221105","https://openalex.org/W2130917146","https://openalex.org/W2132339004","https://openalex.org/W2143719855","https://openalex.org/W2151660570","https://openalex.org/W2151834591","https://openalex.org/W2155117693","https://openalex.org/W2171928131","https://openalex.org/W2176797192","https://openalex.org/W2185726469","https://openalex.org/W2296073425","https://openalex.org/W2437096199","https://openalex.org/W4285719527","https://openalex.org/W6601546654","https://openalex.org/W6604704417","https://openalex.org/W6630570293","https://openalex.org/W6675140444","https://openalex.org/W6685327712"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W2594897229","https://openalex.org/W4290708361","https://openalex.org/W4221142855","https://openalex.org/W3080136773","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W2129812225","https://openalex.org/W2944691285"],"abstract_inverted_index":{"We":[0,34,63],"describe":[1],"how":[2],"to":[3,57],"effectively":[4],"train":[5],"neural":[6,52],"network":[7,53],"based":[8],"language":[9],"models":[10],"on":[11,73,85],"large":[12,81],"data":[13,28],"sets.":[14],"Fast":[15],"convergence":[16],"during":[17],"training":[18,27],"and":[19],"better":[20],"overall":[21],"performance":[22],"is":[23],"observed":[24],"when":[25],"the":[26,51],"are":[29],"sorted":[30],"by":[31],"their":[32],"relevance.":[33],"introduce":[35],"hash-based":[36],"implementation":[37],"of":[38,50,60,69],"a":[39,48],"maximum":[40],"entropy":[41],"model,":[42],"that":[43],"can":[44],"be":[45],"trained":[46,84],"as":[47],"part":[49],"model.":[54],"This":[55],"leads":[56],"significant":[58],"reduction":[59,68],"computational":[61],"complexity.":[62],"achieved":[64],"around":[65],"10%":[66],"relative":[67],"word":[70],"error":[71],"rate":[72],"English":[74],"Broadcast":[75],"News":[76],"speech":[77],"recognition":[78],"task,":[79],"against":[80],"4-gram":[82],"model":[83],"400M":[86],"tokens.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":47},{"year":2020,"cited_by_count":53},{"year":2019,"cited_by_count":61},{"year":2018,"cited_by_count":49},{"year":2017,"cited_by_count":46},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":45},{"year":2014,"cited_by_count":34},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}