{"id":"https://openalex.org/W2171406227","doi":"https://doi.org/10.1109/nlpke.2009.5313764","title":"A statistical method for Uyghur tokenization","display_name":"A statistical method for Uyghur tokenization","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2171406227","doi":"https://doi.org/10.1109/nlpke.2009.5313764","mag":"2171406227"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2009.5313764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","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/A5021370031","display_name":"Batuer Aisha","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Batuer Aisha","raw_affiliation_strings":["Department of Computer Science & Technology State Key Laboratory on Intelligent Technology & Sys, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology State Key Laboratory on Intelligent Technology & Sys, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":["State Key Laboratory on Intelligent Technology & Sys National Laboratory of Information Science & Tech, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory on Intelligent Technology & Sys National Laboratory of Information Science & Tech, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021370031"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81691264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9458000063896179,"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/T14025","display_name":"Educational Technology and Assessment","score":0.9283999800682068,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/lexical-analysis","display_name":"Lexical analysis","score":0.9547552466392517},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7991199493408203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821970582008362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5556535124778748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5353417992591858},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43700939416885376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14321553707122803},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.05572307109832764}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9547552466392517},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7991199493408203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821970582008362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5556535124778748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353417992591858},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43700939416885376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14321553707122803},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.05572307109832764},{"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/nlpke.2009.5313764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399171184","https://openalex.org/W3132926797","https://openalex.org/W4300598845","https://openalex.org/W3204019825","https://openalex.org/W3136915866","https://openalex.org/W4293147636","https://openalex.org/W2601638452","https://openalex.org/W3213294137","https://openalex.org/W2285263069","https://openalex.org/W4376107815"],"abstract_inverted_index":{"Tokenization":[0,8],"is":[1,14,61],"very":[2],"important":[3],"for":[4,35],"Uyghur":[5],"language":[6],"processing.":[7],"of":[9,65],"Uyghur,":[10],"an":[11],"agglutinative":[12],"language,":[13],"quite":[15],"different":[16],"from":[17],"other":[18],"languages":[19],"such":[20],"as":[21],"Chinese":[22],"and":[23,44],"English.":[24],"In":[25],"this":[26],"paper":[27],"we":[28],"propose":[29],"a":[30],"two-steps":[31],"statistical":[32],"tokenization":[33,66],"method":[34,60],"Uyghur.":[36],"Two":[37],"related":[38],"factors,":[39],"the":[40,45,58,63,70],"feature":[41],"template":[42],"scheme":[43],"manually":[46],"tokenized":[47],"corpora,":[48],"are":[49],"also":[50],"discussed.":[51],"The":[52],"preliminary":[53],"experiment":[54],"results":[55],"demonstrate":[56],"that":[57],"proposed":[59],"effective:":[62],"F-measure":[64],"reaches":[67],"88.9%":[68],"in":[69],"open":[71],"test.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}