{"id":"https://openalex.org/W2003151323","doi":"https://doi.org/10.1109/icmlc.2014.7009658","title":"Analysis of smoothing methods for language models on small Chinese corpora","display_name":"Analysis of smoothing methods for language models on small Chinese corpora","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2003151323","doi":"https://doi.org/10.1109/icmlc.2014.7009658","mag":"2003151323"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2014.7009658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2014.7009658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Machine Learning and Cybernetics","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/A5011609119","display_name":"Ming-Chun Liou","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":"Ming-Chun Liou","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National United University, MaioLi, Taiwan","Department of Computer Science and Information Engineering, National United University, MaioLi, 360, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National United University, MaioLi, Taiwan","institution_ids":["https://openalex.org/I125934054"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National United University, MaioLi, 360, Taiwan","institution_ids":["https://openalex.org/I125934054"]}]},{"author_position":"middle","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":"Feng-Long Huang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National United University, MaioLi, Taiwan","Department of Computer Science and Information Engineering, National United University, MaioLi, 360, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National United University, MaioLi, Taiwan","institution_ids":["https://openalex.org/I125934054"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National United University, MaioLi, 360, Taiwan","institution_ids":["https://openalex.org/I125934054"]}]},{"author_position":"middle","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":"Ming-Shing Yu","raw_affiliation_strings":["Department of Computer Science, National Chung-Hsing University, Taichung, Taiwan","Department of Computer Science, National Chung Hsing University, Taichung 402, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chung-Hsing University, Taichung, Taiwan","institution_ids":["https://openalex.org/I162838928"]},{"raw_affiliation_string":"Department of Computer Science, National Chung Hsing University, Taichung 402, Taiwan","institution_ids":["https://openalex.org/I162838928"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018179372","display_name":"Yih-Jeng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I5971364","display_name":"Chienkuo Technology University","ror":"https://ror.org/04ahb7r80","country_code":"TW","type":"education","lineage":["https://openalex.org/I5971364"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yih-Jeng Lin","raw_affiliation_strings":["Department of Information Management, ChienKuo Technology University","Department of Information Management, Chienkuo Technology University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Management, ChienKuo Technology University","institution_ids":["https://openalex.org/I5971364"]},{"raw_affiliation_string":"Department of Information Management, Chienkuo Technology University, Taiwan","institution_ids":["https://openalex.org/I5971364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07204944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"499","last_page":"505"},"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":0.9976999759674072,"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":0.9799000024795532,"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/smoothing","display_name":"Smoothing","score":0.9173140525817871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596285343170166},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7148281335830688},{"id":"https://openalex.org/keywords/turing","display_name":"Turing","score":0.6512673497200012},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.46946656703948975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4665496051311493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44857749342918396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3310648202896118},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32049888372421265},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09860089421272278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0817735493183136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0713045597076416}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.9173140525817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596285343170166},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7148281335830688},{"id":"https://openalex.org/C9870796","wikidata":"https://www.wikidata.org/wiki/Q490481","display_name":"Turing","level":2,"score":0.6512673497200012},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.46946656703948975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4665496051311493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44857749342918396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3310648202896118},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32049888372421265},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09860089421272278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0817735493183136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0713045597076416},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2014.7009658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2014.7009658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W179868316","https://openalex.org/W182831726","https://openalex.org/W2033672007","https://openalex.org/W2056492762","https://openalex.org/W2059800182","https://openalex.org/W2063918473","https://openalex.org/W2097927681","https://openalex.org/W2113641473","https://openalex.org/W2121227244","https://openalex.org/W2134237567","https://openalex.org/W2140979028","https://openalex.org/W2163382007","https://openalex.org/W4233559841","https://openalex.org/W6607479096","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063"],"abstract_inverted_index":{"Data":[0],"sparseness":[1,88],"has":[2],"been":[3,15,37],"an":[4],"inherited":[5],"issue":[6,20,85],"of":[7,21,34,44,47,86,92],"statistical":[8],"language":[9,26,93],"models":[10,27],"and":[11,58,70,75],"smoothing":[12,52],"method":[13],"shave":[14],"used":[16],"to":[17,30,82],"resolve":[18],"the":[19,84,110],"zero":[22,48],"count.":[23],"20":[24],"Chinese":[25,32],"from":[28],"1M":[29],"20M":[31],"words":[33],"CGW":[35],"have":[36],"generated":[38],"on":[39,72,89],"small":[40],"sizes":[41,91],"corpus":[42],"because":[43],"worse":[45],"situation":[46],"count":[49],"issue.":[50],"Five":[51],"methods,":[53,67],"such":[54],"as":[55],"Good":[56,60],"Turing":[57,61],"Advanced":[59],"smoothing,":[62],"including":[63],"our":[64,102],"2":[65],"proposed":[66,103],"are":[68],"evaluated":[69],"analyzed":[71],"inside":[73],"testing":[74],"outside":[76],"testing.":[77],"It":[78],"is":[79,101],"shown":[80],"that":[81],"alleviate":[83],"data":[87],"various":[90,111],"models.":[94,112],"The":[95],"best":[96,107],"one":[97],"among":[98],"these":[99],"methods":[100],"YH-B":[104],"which":[105],"performs":[106],"in":[108],"all":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}