{"id":"https://openalex.org/W4391306923","doi":"https://doi.org/10.1109/smc53992.2023.10393961","title":"MiLMo:Minority Multilingual Pre-Trained Language Model","display_name":"MiLMo:Minority Multilingual Pre-Trained Language Model","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391306923","doi":"https://doi.org/10.1109/smc53992.2023.10393961"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10393961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10393961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5011644190","display_name":"Junjie Deng","orcid":"https://orcid.org/0000-0002-5137-8615"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Deng","raw_affiliation_strings":["School of information engineering, Minzu University of China,Beijing,100081","National Language Resources Monitoring and Research Center for Minority Languages"],"affiliations":[{"raw_affiliation_string":"School of information engineering, Minzu University of China,Beijing,100081","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resources Monitoring and Research Center for Minority Languages","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053129731","display_name":"Hanru Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanru Shi","raw_affiliation_strings":["School of information engineering, Minzu University of China,Beijing,100081","National Language Resources Monitoring and Research Center for Minority Languages"],"affiliations":[{"raw_affiliation_string":"School of information engineering, Minzu University of China,Beijing,100081","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resources Monitoring and Research Center for Minority Languages","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010182723","display_name":"Xinhe Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhe Yu","raw_affiliation_strings":["School of information engineering, Minzu University of China,Beijing,100081","National Language Resources Monitoring and Research Center for Minority Languages"],"affiliations":[{"raw_affiliation_string":"School of information engineering, Minzu University of China,Beijing,100081","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resources Monitoring and Research Center for Minority Languages","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022478702","display_name":"Wugedele Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108760","display_name":"Hohhot Minzu College","ror":"https://ror.org/01qhcb906","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210108760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wugedele Bao","raw_affiliation_strings":["Hohhot Minzu College,Hohhot,010000"],"affiliations":[{"raw_affiliation_string":"Hohhot Minzu College,Hohhot,010000","institution_ids":["https://openalex.org/I4210108760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101731298","display_name":"Yuan Sun","orcid":"https://orcid.org/0000-0003-0565-9659"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Sun","raw_affiliation_strings":["School of information engineering, Minzu University of China,Beijing,100081","National Language Resources Monitoring and Research Center for Minority Languages","Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of information engineering, Minzu University of China,Beijing,100081","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resources Monitoring and Research Center for Minority Languages","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773044","display_name":"Xiaobing Zhao","orcid":"https://orcid.org/0000-0003-1217-8650"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Zhao","raw_affiliation_strings":["School of information engineering, Minzu University of China,Beijing,100081","National Language Resources Monitoring and Research Center for Minority Languages"],"affiliations":[{"raw_affiliation_string":"School of information engineering, Minzu University of China,Beijing,100081","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resources Monitoring and Research Center for Minority Languages","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011644190"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73272589,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9807000160217285,"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":0.9807000160217285,"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/computer-science","display_name":"Computer science","score":0.7426146268844604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5838835835456848},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4968905746936798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4841814339160919},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34484192728996277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426146268844604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5838835835456848},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4968905746936798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4841814339160919},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34484192728996277},{"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/smc53992.2023.10393961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10393961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2206373005","https://openalex.org/W2265846598","https://openalex.org/W2373026019","https://openalex.org/W2378366399","https://openalex.org/W2517194566","https://openalex.org/W2592249290","https://openalex.org/W2740721704","https://openalex.org/W2763150156","https://openalex.org/W2914120296","https://openalex.org/W2952638691","https://openalex.org/W2962784628","https://openalex.org/W2963626623","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W3011411500","https://openalex.org/W3035390927","https://openalex.org/W3118106810","https://openalex.org/W3169483174","https://openalex.org/W4205509257","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6713582272","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6767737316","https://openalex.org/W6768021236","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6809982797"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-trained":[0],"language":[1,26,75,99],"models":[2,27,51],"are":[3,218],"trained":[4,30],"on":[5,16,31,49,54,63,97,116,220],"large-scale":[6],"unsupervised":[7],"data,":[8],"and":[9,20,34,70,106,119,138,151,192,212],"they":[10],"can":[11,28,37,77],"fine-tune":[12],"the":[13,35,42,47,71,110,121,124,148,152,156,167,180,183,189,196],"model":[14,36,76,91,142,150,154,185,207,211],"only":[15],"small-scale":[17],"labeled":[18],"datasets,":[19],"achieve":[21],"good":[22],"results.":[23],"Multilingual":[24],"pre-trained":[25,50,74,90,153,184,206],"be":[29],"multiple":[32,39],"languages,":[33,69],"understand":[38],"languages":[40,65,118],"at":[41],"same":[43],"time.":[44],"At":[45],"present,":[46],"search":[48],"mainly":[52],"focuses":[53],"rich":[55],"resources,":[56],"while":[57],"there":[58],"is":[59,186],"relatively":[60],"little":[61],"research":[62,170],"low-resource":[64],"such":[66],"as":[67],"minority":[68,82,98,117,131,172,200],"public":[72],"multilingual":[73,89,132,201,205,209,213],"not":[78],"work":[79],"well":[80],"for":[81,143,166],"languages.":[83,173],"Therefore,":[84],"this":[85,127,160],"paper":[86,128,161],"constructs":[87,129],"a":[88,130,140],"named":[92,136],"MiLMo":[93,125],"that":[94,179],"performs":[95],"better":[96,187],"tasks,":[100],"including":[101],"Mongolian,":[102],"Tibetan,":[103],"Uyghur,":[104],"Kazakh":[105],"Korean.":[107],"To":[108],"solve":[109],"problem":[111],"of":[112,114,123,171,182],"scarcity":[113],"datasets":[115],"verify":[120],"effectiveness":[122],"model,":[126,191],"text":[133,157,202,214],"classification":[134,158,215],"dataset":[135,216],"MiTC,":[137],"trains":[139],"word2vec":[141,149,190,210],"each":[144],"language.":[145],"By":[146],"comparing":[147],"in":[155,199],"task,":[159],"provides":[162],"an":[163],"optimal":[164],"scheme":[165],"downstream":[168],"task":[169],"The":[174,204],"final":[175],"experimental":[176],"results":[177,198],"show":[178],"performance":[181],"than":[188],"it":[193],"has":[194],"achieved":[195],"best":[197],"classification.":[203],"MiLMo,":[208],"MiTC":[217],"published":[219],"https://milmo.cmli-nlp.com/.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}