{"id":"https://openalex.org/W2397861987","doi":"https://doi.org/10.21437/eurospeech.1995-312","title":"Algorithms for bigram and trigram word clustering","display_name":"Algorithms for bigram and trigram word clustering","publication_year":1995,"publication_date":"1995-09-18","ids":{"openalex":"https://openalex.org/W2397861987","doi":"https://doi.org/10.21437/eurospeech.1995-312","mag":"2397861987"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1995-312","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","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/A5103615266","display_name":"Sven Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sven Martin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066984841","display_name":"J\u00f6rg Liermann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00f6rg Liermann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103615266"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7783,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88035456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1253","last_page":"1256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9915000200271606,"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/T12031","display_name":"Speech and dialogue systems","score":0.9782999753952026,"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/bigram","display_name":"Bigram","score":0.9849328994750977},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.9823489189147949},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9765183925628662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910245060920715},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7124623656272888},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6739063262939453},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6334682703018188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6095048785209656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5170584321022034},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5017166137695312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4138326644897461},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3742293119430542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1297416090965271}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9849328994750977},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.9823489189147949},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9765183925628662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910245060920715},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7124623656272888},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6739063262939453},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6334682703018188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6095048785209656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5170584321022034},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5017166137695312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4138326644897461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3742293119430542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1297416090965271},{"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:10.21437/eurospeech.1995-312","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1903115690","https://openalex.org/W2397861987","https://openalex.org/W2105076537","https://openalex.org/W2041167939","https://openalex.org/W2056250865","https://openalex.org/W1700330385","https://openalex.org/W2020757772","https://openalex.org/W2002221802","https://openalex.org/W2250909759","https://openalex.org/W2223833155"],"abstract_inverted_index":{"Abstract":[0],"In":[3],"this":[4,35],"paper,":[5],"we":[6],"describe":[7],"an":[8,22,55],"efficient":[9,56],"method":[10,20],"for":[11,15,58],"obtaining":[12],"word":[13,93,101],"classes":[14],"class":[16,42,48],"language":[17,102],"models.":[18],"The":[19,31],"employs":[21],"exchange":[23],"algorithm":[24],"using":[25],"the":[26,38,41,47,52,61,64,70],"criterion":[27,45],"of":[28,34,40,54,69,81,92],"perplexity":[29,44,50],"improvement.":[30],"novel":[32],"contributions":[33],"paper":[36],"are":[37],"extension":[39],"bigram":[43],"to":[46,100],"trigram":[49],"criterion,":[51],"description":[53],"implementation":[57],"speeding":[59],"up":[60],"clustering":[62,71],"process,":[63],"detailed":[65],"computational":[66],"complexity":[67],"analysis":[68],"algorithm,":[72],"and,":[73],"finally,":[74],"experimental":[75],"results":[76],"on":[77],"large":[78],"text":[79],"corpora":[80],"about":[82],"1,":[83],"4,":[84],"39":[85],"and":[86,104],"241":[87],"million":[88],"words":[89],"including":[90],"examples":[91],"classes,":[94],"test":[95],"corpus":[96],"perplexities":[97],"in":[98],"comparison":[99],"models,":[103],"speech":[105],"recognition":[106],"results.":[107]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}