{"id":"https://openalex.org/W1539309091","doi":"https://doi.org/10.21437/interspeech.2014-564","title":"One billion word benchmark for measuring progress in statistical language modeling","display_name":"One billion word benchmark for measuring progress in statistical language modeling","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W1539309091","doi":"https://doi.org/10.21437/interspeech.2014-564","mag":"1539309091"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-564","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1312.3005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068010225","display_name":"Ciprian Chelba","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ciprian Chelba","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113452656","display_name":"Mike Schuster","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Schuster","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070804876","display_name":"Qi Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Ge","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076738898","display_name":"Thorsten Brants","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thorsten Brants","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048132414","display_name":"Phillipp Koehn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phillipp Koehn","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103532312","display_name":"Tony Robinson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tony Robinson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068010225"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.4783,"has_fulltext":true,"cited_by_count":91,"citation_normalized_percentile":{"value":0.97573445,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2635","last_page":"2639"},"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":0.9998000264167786,"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":0.9975000023841858,"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":0.8484348058700562},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8420278429985046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737186074256897},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7082158923149109},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.663783848285675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262899994850159},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5145217776298523},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4974868595600128},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.47049757838249207},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.42457112669944763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40362584590911865},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09696301817893982},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07797285914421082}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8484348058700562},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8420278429985046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737186074256897},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7082158923149109},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.663783848285675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262899994850159},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5145217776298523},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4974868595600128},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.47049757838249207},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.42457112669944763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40362584590911865},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09696301817893982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07797285914421082},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2014-564","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1312.3005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.3005","pdf_url":"https://arxiv.org/pdf/1312.3005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2951714314","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1312.3005","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.748.5495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.748.5495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1312.3005.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1312.3005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1312.3005","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:1539309091","is_oa":false,"landing_page_url":"http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41880.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1312.3005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.3005","pdf_url":"https://arxiv.org/pdf/1312.3005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1539309091.pdf","grobid_xml":"https://content.openalex.org/works/W1539309091.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W10704533","https://openalex.org/W36903255","https://openalex.org/W62305045","https://openalex.org/W115367774","https://openalex.org/W161283806","https://openalex.org/W179875071","https://openalex.org/W1590952807","https://openalex.org/W1934041838","https://openalex.org/W1970689298","https://openalex.org/W1989705153","https://openalex.org/W2020382207","https://openalex.org/W2026383756","https://openalex.org/W2050971845","https://openalex.org/W2071315630","https://openalex.org/W2072223048","https://openalex.org/W2091812280","https://openalex.org/W2100714283","https://openalex.org/W2109664771","https://openalex.org/W2110485445","https://openalex.org/W2132339004","https://openalex.org/W2134237567","https://openalex.org/W2158148237","https://openalex.org/W2397435450","https://openalex.org/W2402268235","https://openalex.org/W2950186769"],"related_works":["https://openalex.org/W2963403868","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2962739339","https://openalex.org/W2153579005","https://openalex.org/W2611669587","https://openalex.org/W2964308564","https://openalex.org/W2259472270","https://openalex.org/W2132339004","https://openalex.org/W179875071","https://openalex.org/W2130942839","https://openalex.org/W1840435438","https://openalex.org/W2963969878","https://openalex.org/W2963012544","https://openalex.org/W2962718684","https://openalex.org/W2799194071","https://openalex.org/W1614298861","https://openalex.org/W1566289585"],"abstract_inverted_index":{"We":[0,49],"propose":[1],"a":[2,65,81,105],"new":[3],"benchmark":[4,27,101],"corpus":[5],"to":[6,31,39,86,112],"be":[7,29],"used":[8],"for":[9,123,133],"measuring":[10],"progress":[11],"in":[12,89,94,126],"statistical":[13],"language":[14,35,57,70],"modeling.":[15],"With":[16],"almost":[17],"one":[18],"billion":[19],"words":[20],"of":[21,52,56,83,128,135],"training":[22],"data,":[23,116],"we":[24],"hope":[25],"this":[26],"will":[28],"useful":[30],"quickly":[32],"evaluate":[33],"novel":[34],"modeling":[36],"techniques,":[37],"and":[38],"compare":[40],"their":[41],"contribution":[42],"when":[43],"combined":[44],"with":[45,59,64],"other":[46],"advanced":[47],"techniques.":[48],"show":[50],"performance":[51],"several":[53],"well-known":[54],"types":[55],"models,":[58],"the":[60,109,114,136],"best":[61],"results":[62],"achieved":[63],"recurrent":[66],"neural":[67],"network":[68],"based":[69],"model.":[71],"The":[72,100],"baseline":[73,137],"unpruned":[74],"Kneser-Ney":[75],"5-gram":[76],"model":[77],"achieves":[78],"perplexity":[79],"67.6;":[80],"combination":[82],"techniques":[84],"leads":[85],"35%":[87],"reduction":[88,93],"perplexity,":[90],"or":[91],"10%":[92],"cross-entropy":[95],"(bits),":[96],"over":[97],"that":[98],"baseline.":[99],"is":[102],"available":[103,120],"as":[104],"code.google.com":[106],"project;":[107],"besides":[108],"scripts":[110],"needed":[111],"rebuild":[113],"training/held-out":[115],"it":[117],"also":[118],"makes":[119],"log-probability":[121],"values":[122],"each":[124,127,134],"word":[125],"ten":[129],"held-out":[130],"data":[131],"sets,":[132],"n-gram":[138],"models.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}