{"id":"https://openalex.org/W2922341783","doi":"https://doi.org/10.23919/apsipa.2018.8659698","title":"Multilingual Stemming and Term extraction for Uyghur, Kazak and Kirghiz","display_name":"Multilingual Stemming and Term extraction for Uyghur, Kazak and Kirghiz","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922341783","doi":"https://doi.org/10.23919/apsipa.2018.8659698","mag":"2922341783"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659698","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5023562009","display_name":"Mijit Ablimit","orcid":"https://orcid.org/0009-0008-0781-4150"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mijit Ablimit","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079392405","display_name":"Sardar Parhat","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sardar Parhat","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075133420","display_name":"Askar Hamdulla","orcid":"https://orcid.org/0000-0002-2321-308X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Askar Hamdulla","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"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":"Thomas Fang Zheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023562009"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.19325885,"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":"587","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9771000146865845,"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/agglutinative-language","display_name":"Agglutinative language","score":0.8873889446258545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8768309354782104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6914511919021606},{"id":"https://openalex.org/keywords/affix","display_name":"Affix","score":0.6650357246398926},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6511146426200867},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6493028402328491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271213293075562},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.6189374327659607},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6131202578544617},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4857943058013916},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4577052593231201},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.41974878311157227},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3350718319416046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32314980030059814},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17705297470092773}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8873889446258545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8768309354782104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6914511919021606},{"id":"https://openalex.org/C2778428490","wikidata":"https://www.wikidata.org/wiki/Q62155","display_name":"Affix","level":2,"score":0.6650357246398926},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6511146426200867},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6493028402328491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271213293075562},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.6189374327659607},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6131202578544617},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4857943058013916},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4577052593231201},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.41974878311157227},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3350718319416046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32314980030059814},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17705297470092773},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659698","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W2029306354","https://openalex.org/W2094544353","https://openalex.org/W2096473075","https://openalex.org/W2588319948","https://openalex.org/W2786149404","https://openalex.org/W2950577311"],"related_works":["https://openalex.org/W4387743929","https://openalex.org/W2251416744","https://openalex.org/W2501899044","https://openalex.org/W2977444986","https://openalex.org/W2485012912","https://openalex.org/W2070307934","https://openalex.org/W2013556410","https://openalex.org/W2393148272","https://openalex.org/W94825293","https://openalex.org/W2003843193"],"abstract_inverted_index":{"Stemming":[0],"and":[1,7,18,39,43,46,52,71,82,101,115,121,129],"term":[2,53,145],"extraction":[3,111,146],"is":[4],"an":[5],"important":[6],"difficult":[8],"step":[9],"on":[10,50,60,62,66],"NLP":[11],"for":[12,24,98],"low":[13],"resource":[14],"languages.":[15,28,103],"Inflectional":[16],"structure":[17],"noisy":[19,151],"data":[20],"aggravate":[21],"this":[22,137],"problem":[23],"less":[25],"popular":[26],"agglutinative":[27],"A":[29],"morphological":[30,95],"analyzer":[31],"with":[32,112,134],"the":[33,76,87],"longer":[34,122],"context":[35,81,123],"can":[36,106,125],"utilize":[37],"resources":[38],"provide":[40,107],"reliable":[41,142],"semantic":[42],"syntactic":[44],"information,":[45],"effectively":[47],"reduce":[48],"ambiguity":[49],"stemming":[51,61],"detection.":[54],"There":[55],"are":[56],"some":[57],"previous":[58],"works":[59],"Uyghur":[63],"texts":[64],"based":[65],"simple":[67],"morphology":[68],"like":[69,118],"affix":[70],"manually":[72],"collected":[73],"rules.":[74],"But":[75],"limited":[77],"information":[78],"of":[79,144,150],"smaller":[80],"lower":[83],"segmentation":[84],"accuracy":[85],"cost":[86],"reliability.":[88],"We":[89],"developed":[90],"a":[91,140],"sentence":[92,108],"level":[93,109],"multilingual":[94],"processing":[96],"tool":[97,105,138],"Uyghur,":[99],"Kazak,":[100],"Kirghiz":[102],"This":[104],"morpheme":[110],"98%":[113],"accuracy,":[114],"further":[116],"analysis":[117],"word":[119,135],"embedding":[120,136],"modelling":[124],"extract":[126],"remaining":[127],"unseen":[128],"infrequent":[130],"stems":[131],"reliably.":[132],"Combined":[133],"provides":[139],"more":[141],"way":[143],"from":[147,154],"large":[148],"number":[149],"text":[152],"available":[153],"internet.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}