{"id":"https://openalex.org/W89634226","doi":"https://doi.org/10.21437/icslp.2000-597","title":"Beyond the conventional statistical language models: the variable-length sequences approach","display_name":"Beyond the conventional statistical language models: the variable-length sequences approach","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W89634226","doi":"https://doi.org/10.21437/icslp.2000-597","mag":"89634226"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-597","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00099107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108365460","display_name":"Imed Zitouni","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Imed Zitouni","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090778317","display_name":"Kamel Sma\u0131\u0308li","orcid":"https://orcid.org/0000-0002-4237-7303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamel Sma\u00efli","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403479","display_name":"Jean-Paul Haton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Paul Haton","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108365460"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5305,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73769991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"vol. 3, 562","last_page":"565"},"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":0.9987000226974487,"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":0.9962000250816345,"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":0.9562354683876038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682849168777466},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.724384069442749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7179604768753052},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6800979375839233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6320135593414307},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5630565285682678},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.546057403087616},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5204991698265076},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.49083858728408813},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4689687490463257},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4624600112438202},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4346328377723694},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.43216145038604736},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4276137948036194},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.42226266860961914},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3409305810928345},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21012961864471436},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.10775643587112427}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9562354683876038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682849168777466},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.724384069442749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7179604768753052},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6800979375839233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6320135593414307},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5630565285682678},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.546057403087616},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5204991698265076},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.49083858728408813},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4689687490463257},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4624600112438202},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4346328377723694},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.43216145038604736},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4276137948036194},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.42226266860961914},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3409305810928345},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21012961864471436},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.10775643587112427},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2000-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-597","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:10.1.1.491.2174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.491.2174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.loria.fr/~smaili/Icslp00Imed.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00099107v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00099107","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Speech Language Processing, 2000, P\u00e9kin, China. pp.4","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00099107v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00099107","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Speech Language Processing, 2000, P\u00e9kin, China. pp.4","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W72566427","https://openalex.org/W180514164","https://openalex.org/W184563473","https://openalex.org/W203918880","https://openalex.org/W1513755266","https://openalex.org/W1522352264","https://openalex.org/W1561264958","https://openalex.org/W1607753411","https://openalex.org/W1947630885","https://openalex.org/W2041167939","https://openalex.org/W2096837052","https://openalex.org/W2134237567","https://openalex.org/W2290556554","https://openalex.org/W2530438547","https://openalex.org/W4301386125"],"related_works":["https://openalex.org/W2093729408","https://openalex.org/W2132221452","https://openalex.org/W2393111077","https://openalex.org/W1577263324","https://openalex.org/W2125852914","https://openalex.org/W4255406899","https://openalex.org/W2787311093","https://openalex.org/W2020933619","https://openalex.org/W2169518243","https://openalex.org/W2105076537"],"abstract_inverted_index":{"In":[0,60,103],"natural":[1],"language,":[2],"several":[3,125],"sequences":[4,36,167,208,234],"of":[5,50,100,115,127,152,165,183,194,200,206,231],"words":[6,196],"are":[7,45,58,146,188,224],"very":[8],"frequent.":[9],"A":[10,29],"classical":[11],"language":[12,56,128],"model,":[13,154],"like":[14],"n-gram,":[15],"does":[16],"not":[17],"adequately":[18],"take":[19],"into":[20],"account":[21],"such":[22],"sequences,":[23],"because":[24],"it":[25],"underestimates":[26],"their":[27],"probabilities.":[28],"better":[30],"approach":[31],"consists":[32],"in":[33,75,109,141,181,235],"modelling":[34],"word":[35,52,133,166,207,233],"as":[37,47],"if":[38],"they":[39],"were":[40],"individual":[41],"dictionary":[42],"elements.":[43],"Sequences":[44],"considered":[46],"additional":[48,98],"entries":[49],"the":[51,71,105,113,143,157,163,170,240],"lexicon,":[53],"on":[54,81,92,191],"which":[55,85,96,142,223],"models":[57,129],"computed.":[59],"this":[61,153],"paper,":[62],"we":[63,137],"present":[64,138],"an":[65],"original":[66],"method":[67,78],"for":[68],"automatically":[69],"determining":[70],"most":[72],"important":[73],"phrases":[74],"corpora.":[76],"This":[77],"is":[79,107,162],"based":[80],"information":[82],"theoretic":[83],"criteria,":[84],"insure":[86],"a":[87,117,139,192,198],"high":[88],"statistical":[89],"consistency,":[90],"and":[91,131,185,197],"French":[93],"grammatical":[94],"classes":[95],"include":[97],"type":[99],"linguistic":[101],"dependencies.":[102],"addition,":[104],"perplexity":[106,184,214],"used":[108,159],"order":[110],"to":[111,168,176,221,226],"make":[112],"decision":[114],"selecting":[116],"potential":[118],"sequence":[119],"more":[120,147,216],"accurate.":[121],"We":[122],"propose":[123],"also":[124],"variants":[126],"with":[130,156],"without":[132,173],"sequences.":[134],"Among":[135],"them,":[136],"model":[140],"trigger":[144,160,171],"pairs":[145],"significant":[148],"linguistically.":[149],"The":[150,204,229],"originality":[151],"compared":[155,220],"commonly":[158],"approaches,":[161],"use":[164,205],"estimate":[169],"pair":[172],"limiting":[174],"itself":[175],"single":[177,227],"words.":[178,203,228],"Experimental":[179],"tests,":[180],"terms":[182],"recognition":[186],"rate,":[187],"carried":[189],"out":[190],"vocabulary":[193],"20000":[195],"corpus":[199],"43":[201],"million":[202],"proposed":[209],"by":[210,215,242],"our":[211,236],"algorithm":[212],"reduces":[213],"than":[217],"16":[218],"%":[219],"those,":[222],"limited":[225],"introduction":[230],"these":[232],"dictation":[237],"machine":[238],"improves":[239],"accuracy":[241],"approximately":[243],"15%.":[244],"1.":[245]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}