{"id":"https://openalex.org/W2164517999","doi":"https://doi.org/10.1109/icassp.1996.540320","title":"Clustering words for statistical language models based on contextual word similarity","display_name":"Clustering words for statistical language models based on contextual word similarity","publication_year":2002,"publication_date":"2002-12-23","ids":{"openalex":"https://openalex.org/W2164517999","doi":"https://doi.org/10.1109/icassp.1996.540320","mag":"2164517999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1996.540320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.540320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","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/A5108797965","display_name":"Azarshid Farhat","orcid":null},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"A. Farhat","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, QUE, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031383787","display_name":"Joanna Isabelle","orcid":null},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J.-F. Isabelle","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, QUE, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011489869","display_name":"Douglas O\u2019Shaughnessy","orcid":"https://orcid.org/0000-0002-0110-2346"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"D. O'Shaughnessy","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, QUE, Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.8529,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79813988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"180","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9933000206947327,"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":0.9889000058174133,"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":0.9373849630355835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8266102075576782},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7715556621551514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7078287601470947},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7072668671607971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6378729343414307},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6134201884269714},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5941753387451172},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5875925421714783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42886656522750854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1030532717704773}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9373849630355835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266102075576782},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7715556621551514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7078287601470947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7072668671607971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6378729343414307},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6134201884269714},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5941753387451172},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5875925421714783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42886656522750854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1030532717704773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/icassp.1996.540320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.540320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W3720092","https://openalex.org/W47415966","https://openalex.org/W62980115","https://openalex.org/W1561264958","https://openalex.org/W1585489087","https://openalex.org/W1597533204","https://openalex.org/W2105117008","https://openalex.org/W2110993209","https://openalex.org/W2121227244","https://openalex.org/W2134237567","https://openalex.org/W2441154163","https://openalex.org/W6600153489","https://openalex.org/W6601957796","https://openalex.org/W6633503704","https://openalex.org/W6635138082","https://openalex.org/W6635726886","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745","https://openalex.org/W2944691285"],"abstract_inverted_index":{"This":[0,30],"paper":[1],"describes":[2],"a":[3,26,57],"new":[4],"word":[5,22,47,51],"clustering":[6,28,31],"approach":[7,18],"for":[8],"statistical":[9],"language":[10],"modeling.":[11],"The":[12],"classification":[13,48],"criteria":[14],"used":[15,24],"by":[16,54],"our":[17],"is":[19],"the":[20,36,41,50],"contextual":[21],"similarity":[23],"in":[25],"simplified":[27],"algorithm.":[29],"technique":[32],"was":[33],"tested":[34],"on":[35],"INRS":[37],"speech":[38],"recognizer":[39],"using":[40],"spontaneous":[42],"English":[43],"corpora,":[44],"ATIS.":[45],"Automatic":[46],"increases":[49],"accuracy":[52],"rate":[53],"8.6%":[55],"with":[56],"perplexity":[58],"reduction":[59],"about":[60],"of":[61],"6.9%.":[62]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}