{"id":"https://openalex.org/W2135777451","doi":"https://doi.org/10.3115/1073083.1073115","title":"Exploring asymmetric clustering for statistical language modeling","display_name":"Exploring asymmetric clustering for statistical language modeling","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2135777451","doi":"https://doi.org/10.3115/1073083.1073115","mag":"2135777451"},"language":"en","primary_location":{"id":"doi:10.3115/1073083.1073115","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073115","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073115","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, P.R.C"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, P.R.C","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110237290","display_name":"Joshua Goodman","orcid":null},"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":"Joshua T. Goodman","raw_affiliation_strings":["Microsoft Research, Redmond, Washington"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, Washington","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110660237","display_name":"Guihong Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guihong Cao","raw_affiliation_strings":["Tianjin Univerisity, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Univerisity, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455112","display_name":"Hang Li","orcid":"https://orcid.org/0000-0001-5096-0155"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Microsoft Research, Asia Beijing, P.R.C"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia Beijing, P.R.C","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114910293"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.6366,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87762994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9904000163078308,"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":0.755994975566864},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6986438035964966},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6869525909423828},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6629530787467957},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6177549362182617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999899506568909},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.592747151851654},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5239325165748596},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.5120294690132141},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4638645052909851},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.44632643461227417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1800958216190338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755994975566864},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6986438035964966},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6869525909423828},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6629530787467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6177549362182617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999899506568909},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.592747151851654},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5239325165748596},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.5120294690132141},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4638645052909851},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.44632643461227417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1800958216190338},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1073083.1073115","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073115","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.9518","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.9518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P02/P02-1024.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1073083.1073115","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073115","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073115","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135777451.pdf","grobid_xml":"https://content.openalex.org/works/W2135777451.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W47415966","https://openalex.org/W79835312","https://openalex.org/W95416423","https://openalex.org/W1549285799","https://openalex.org/W1797288984","https://openalex.org/W1974967573","https://openalex.org/W2058045861","https://openalex.org/W2075201173","https://openalex.org/W2097333193","https://openalex.org/W2100506586","https://openalex.org/W2111305191","https://openalex.org/W2121227244","https://openalex.org/W2127314673","https://openalex.org/W2134237567","https://openalex.org/W2140842551","https://openalex.org/W2145826596","https://openalex.org/W2155852061","https://openalex.org/W2162965720","https://openalex.org/W2165112885","https://openalex.org/W2441154163","https://openalex.org/W2951328679","https://openalex.org/W4255764218","https://openalex.org/W4285719527","https://openalex.org/W6638218882","https://openalex.org/W6674571003","https://openalex.org/W6676699771","https://openalex.org/W6678277124","https://openalex.org/W6679063059"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2057384730","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404"],"abstract_inverted_index":{"The":[0,24,114],"n-gram":[1,26,33,145],"model":[2,27,34,85,150],"is":[3,28,78,119],"a":[4,21,29,97,122],"stochastic":[5],"model,":[6],"which":[7,36,69],"predicts":[8],"the":[9,15,32,42,71,79,82,101,108,112,117,135,148,156,159,163,166],"next":[10],"word":[11,22,144],"(predicted":[12],"word)":[13],"given":[14],"previous":[16],"words":[17,38,57],"(conditional":[18],"words)":[19],"in":[20,35,41,88,106,137,162],"sequence.":[23],"cluster":[25,60,67,84,141],"variant":[30],"of":[31,81,100,110,116,134,158,165],"similar":[37],"are":[39,63],"classified":[40],"same":[43,72,149],"cluster.":[44],"It":[45],"has":[46],"been":[47],"demonstrated":[48],"that":[49,62,155],"using":[50],"different":[51],"clusters":[52,73],"for":[53,74],"predicted":[54],"and":[55,143],"conditional":[56],"leads":[58],"to":[59,65],"models":[61,68,142,146],"superior":[64],"classical":[66,140],"use":[70],"both":[75],"words.":[76],"This":[77],"basis":[80],"asymmetric":[83],"(ACM)":[86],"discussed":[87],"our":[89],"study.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94],"first":[95],"present":[96],"formal":[98],"definition":[99],"ACM.":[102,113],"We":[103],"then":[104],"describe":[105],"detail":[107],"methodology":[109],"constructing":[111],"effectiveness":[115],"ACM":[118,136,160],"evaluated":[120],"on":[121],"realistic":[123],"application,":[124],"namely":[125],"Japanese":[126],"Kana-Kanji":[127],"conversion.":[128],"Experimental":[129],"results":[130],"show":[131],"substantial":[132],"improvements":[133],"comparison":[138],"with":[139],"at":[147],"size.":[151],"Our":[152],"analysis":[153],"shows":[154],"high-performance":[157],"lies":[161],"asymmetry":[164],"model.":[167]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}