{"id":"https://openalex.org/W2130335503","doi":"https://doi.org/10.1109/icsmc.2004.1400926","title":"Study on good-turing and a novel smoothing method based on real corpora for language models","display_name":"Study on good-turing and a novel smoothing method based on real corpora for language models","publication_year":2005,"publication_date":"2005-04-12","ids":{"openalex":"https://openalex.org/W2130335503","doi":"https://doi.org/10.1109/icsmc.2004.1400926","mag":"2130335503"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1400926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1400926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5091610455","display_name":"Feng-Long Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I125934054","display_name":"National United University","ror":"https://ror.org/04twccc71","country_code":"TW","type":"education","lineage":["https://openalex.org/I125934054"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huang Feng-Long","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National United University, Miao-Li, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National United University, Miao-Li, Taiwan","institution_ids":["https://openalex.org/I125934054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100968486","display_name":"Ming\u2010Shing Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Ming-Shing","raw_affiliation_strings":["Department of Information Science, National Chung Hsing University, Taichung, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science, National Chung Hsing University, Taichung, Taiwan","institution_ids":["https://openalex.org/I162838928"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.24062668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"3741","last_page":"3745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980000257492065,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/smoothing","display_name":"Smoothing","score":0.9331684112548828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735490083694458},{"id":"https://openalex.org/keywords/turing","display_name":"Turing","score":0.570724368095398},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4983217716217041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3746296167373657},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3568740487098694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3495520353317261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11134353280067444},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07495269179344177}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.9331684112548828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735490083694458},{"id":"https://openalex.org/C9870796","wikidata":"https://www.wikidata.org/wiki/Q490481","display_name":"Turing","level":2,"score":0.570724368095398},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4983217716217041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3746296167373657},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3568740487098694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3495520353317261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11134353280067444},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07495269179344177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2004.1400926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1400926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W175958223","https://openalex.org/W182831726","https://openalex.org/W1934041838","https://openalex.org/W2020749563","https://openalex.org/W2059800182","https://openalex.org/W2110993209","https://openalex.org/W2113641473","https://openalex.org/W2121227244","https://openalex.org/W2134237567","https://openalex.org/W2150888885","https://openalex.org/W2158195707","https://openalex.org/W2163306339","https://openalex.org/W2168938909","https://openalex.org/W4233559841","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W2051487156","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W2073681303"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,26,66,82,91,134],"well-known":[6],"Good-Turing":[7,61],"smoothing":[8,20,40,49,71,86,98,137],"technique,":[9],"which":[10,79],"has":[11],"inherited":[12],"issue":[13],"and":[14,43],"propose":[15,69],"a":[16],"novel":[17,70],"method.":[18,67,87],"The":[19,45,108,120,127],"method":[21,50,101,124],"is":[22,51,102,125],"used":[23,63,95],"to":[24,64,90,132],"resolve":[25],"zero":[27],"count":[28],"problems":[29],"in":[30],"traditional":[31],"language":[32],"models.":[33],"Basically,":[34],"there":[35],"are":[36,62,130],"two":[37],"processes":[38],"for":[39,60,112],"techniques:":[41],"discounting":[42],"redistributing.":[44],"statistical":[46],"behavior":[47,84,121],"of":[48,85,110,122,136],"analyzed":[52],"on":[53,74,104],"various":[54],"training":[55,76,106],"data":[56,77],"size.":[57],"Several":[58],"features":[59],"improve":[65],"We":[68],"methods":[72],"based":[73,103],"real":[75,105],"sets,":[78],"will":[80],"reflect":[81],"physical":[83],"With":[88],"respect":[89],"heuristic":[92],"probability":[93],"assignment":[94],"by":[96],"most":[97],"methods,":[99],"our":[100,123],"corpora.":[107],"curves":[109],"number":[111],"events":[113],"with":[114],"different":[115],"counts":[116],"can":[117],"be":[118],"plotted.":[119],"analyzed.":[126],"empirical":[128],"results":[129],"presented":[131],"compare":[133],"effectiveness":[135],"methods.":[138]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}