{"id":"https://openalex.org/W2802184895","doi":"https://doi.org/10.1109/icassp.2018.8461734","title":"Whole Sentence Neural Language Models","display_name":"Whole Sentence Neural Language Models","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802184895","doi":"https://doi.org/10.1109/icassp.2018.8461734","mag":"2802184895"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"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":"Yinghui Huang","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","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 T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"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":"Kartik Audhkhasi","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","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 T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"6089","last_page":"6093"},"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":0.9998000264167786,"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":0.9994000196456909,"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":0.8614027500152588},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7631773948669434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6563405990600586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6253379583358765},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5818008780479431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5250791907310486},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5203877687454224},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5056846141815186},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.49857211112976074},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4791547656059265},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4483543336391449},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.44759610295295715},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4235674738883972},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.42346641421318054},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41834181547164917},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31277555227279663},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.19939309358596802},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1274893581867218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614027500152588},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7631773948669434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563405990600586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6253379583358765},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5818008780479431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5250791907310486},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5203877687454224},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5056846141815186},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.49857211112976074},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4791547656059265},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4483543336391449},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44759610295295715},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4235674738883972},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.42346641421318054},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41834181547164917},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31277555227279663},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.19939309358596802},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1274893581867218},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W17608502","https://openalex.org/W179314280","https://openalex.org/W179875071","https://openalex.org/W194986311","https://openalex.org/W932413789","https://openalex.org/W1520465330","https://openalex.org/W1749358154","https://openalex.org/W1773599773","https://openalex.org/W1832693441","https://openalex.org/W2015840095","https://openalex.org/W2064675550","https://openalex.org/W2083751884","https://openalex.org/W2113457868","https://openalex.org/W2114524997","https://openalex.org/W2120861206","https://openalex.org/W2138204974","https://openalex.org/W2153579005","https://openalex.org/W2158148237","https://openalex.org/W2159697950","https://openalex.org/W2245569228","https://openalex.org/W2962722345","https://openalex.org/W2963266252","https://openalex.org/W3138475383","https://openalex.org/W4294170691","https://openalex.org/W4295803813","https://openalex.org/W6600728236","https://openalex.org/W6607185345","https://openalex.org/W6607333740","https://openalex.org/W6624558595","https://openalex.org/W6637681180","https://openalex.org/W6638082434","https://openalex.org/W6655723563","https://openalex.org/W6678040779","https://openalex.org/W6683499437","https://openalex.org/W6684953378","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2071315630","https://openalex.org/W2897427480","https://openalex.org/W1745277","https://openalex.org/W2787311093","https://openalex.org/W1508853749","https://openalex.org/W2624072012"],"abstract_inverted_index":{"Recurrent":[0,26],"neural":[1,112],"networks":[2],"have":[3],"become":[4],"increasingly":[5],"popular":[6],"for":[7,57,145],"the":[8,40,52,64,70,74,91,94,120,126,179],"task":[9],"of":[10,55,68,93,160,182],"language":[11,22,49,59,113,137],"modeling":[12,180],"achieving":[13],"impressive":[14],"gains":[15],"in":[16,96],"state-of-the-art":[17],"speech":[18,174],"recognition":[19,175],"and":[20,177],"natural":[21],"processing":[23],"(NLP)":[24],"tasks.":[25],"models":[27,60,114,134,138,150],"exploit":[28],"word":[29,72,77,122],"dependencies":[30],"over":[31],"a":[32,117,158],"much":[33],"longer":[34],"context":[35],"window":[36],"(as":[37],"retained":[38],"by":[39],"history":[41],"states)":[42],"than":[43],"what":[44],"is":[45],"feasible":[46],"with":[47],"n-gram":[48],"models.":[50],"However":[51],"training":[53],"criterion":[54],"choice":[56],"recurrent":[58,136],"continues":[61],"to":[62,119,135,170],"be":[63],"local":[65,81],"conditional":[66],"likelihood":[67],"generating":[69],"current":[71],"given":[73],"(pos-sibly":[75],"long)":[76],"context,":[78],"thus":[79],"making":[80],"decisions":[82],"at":[83,109],"each":[84],"word.":[85],"This":[86],"locally-conditional":[87],"design":[88],"fundamentally":[89,152],"limits":[90],"ability":[92],"model":[95],"exploiting":[97],"whole":[98,110,130],"sentence":[99,111,131,149],"structures.":[100],"In":[101],"this":[102,183],"paper,":[103],"we":[104],"present":[105,155],"our":[106],"initial":[107],"results":[108,156],"which":[115],"assign":[116],"probability":[118],"entire":[121],"sequence.":[123],"We":[124,154],"extend":[125],"previous":[127],"work":[128],"on":[129,157],"maximum":[132],"entropy":[133],"while":[139],"using":[140],"Noise":[141],"Contrastive":[142],"Estimation":[143],"(NCE)":[144],"training,":[146],"as":[147],"these":[148],"are":[151],"un-normalizable.":[153],"range":[159],"tasks:":[161],"from":[162],"sequence":[163],"identification":[164],"tasks":[165],"such":[166],"as,":[167],"palindrome":[168],"detection":[169],"large":[171],"vocabulary":[172],"automatic":[173],"(LVCSR)":[176],"demonstrate":[178],"power":[181],"approach.":[184]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}