{"id":"https://openalex.org/W4402351486","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650812","title":"Pre-training Language Model for Mongolian with Agglutinative Linguistic Knowledge Injection","display_name":"Pre-training Language Model for Mongolian with Agglutinative Linguistic Knowledge Injection","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351486","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650812"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5015872107","display_name":"Muhan Na","orcid":"https://orcid.org/0000-0002-8104-1749"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhan Na","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716022","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-8227-6064"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9994000196456909,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9636359214782715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152299880981445},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5700457096099854},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5566596388816833},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.47162413597106934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4572006165981293},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08208274841308594}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.9636359214782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152299880981445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5700457096099854},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5566596388816833},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47162413597106934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4572006165981293},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08208274841308594},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.0},{"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/ijcnn60899.2024.10650812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2144578941","https://openalex.org/W2148437670","https://openalex.org/W2751936342","https://openalex.org/W2769068044","https://openalex.org/W2887428522","https://openalex.org/W2896457183","https://openalex.org/W2938830017","https://openalex.org/W2943064529","https://openalex.org/W2952370363","https://openalex.org/W2965373594","https://openalex.org/W2995923603","https://openalex.org/W2996398592","https://openalex.org/W3034999214","https://openalex.org/W3088577908","https://openalex.org/W3106690208","https://openalex.org/W3154596443","https://openalex.org/W3197319555","https://openalex.org/W3209984917","https://openalex.org/W3216225167","https://openalex.org/W4237871605","https://openalex.org/W4285232264","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4304013646","https://openalex.org/W4312629998","https://openalex.org/W4312877428","https://openalex.org/W4385245566","https://openalex.org/W4390480998","https://openalex.org/W4392903647","https://openalex.org/W6730051900","https://openalex.org/W6731819051","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6761910064","https://openalex.org/W6766668698","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6779857854","https://openalex.org/W6793736971","https://openalex.org/W6810723814","https://openalex.org/W6849669386","https://openalex.org/W6852786374","https://openalex.org/W6858297017"],"related_works":["https://openalex.org/W2728343294","https://openalex.org/W4387891631","https://openalex.org/W4387913002","https://openalex.org/W2896235912","https://openalex.org/W2099456648","https://openalex.org/W3204019825","https://openalex.org/W3136915866","https://openalex.org/W2165316507","https://openalex.org/W44901218","https://openalex.org/W2947417049"],"abstract_inverted_index":{"BERT":[0,191],"based":[1],"Pre-training":[2],"Language":[3],"Model":[4],"(PLM)":[5],"has":[6,38],"become":[7],"a":[8,70,79,103,111,152],"crucial":[9],"step":[10],"in":[11,16,199],"achieving":[12],"the":[13,24,42,52,59,74,92,97,118,130,133,139,145,189],"best":[14],"results":[15,179],"various":[17],"natural":[18],"language":[19,197],"processing":[20],"(NLP)":[21],"tasks.":[22],"However,":[23],"current":[25],"progress,":[26],"which":[27],"mainly":[28],"focuses":[29],"on":[30,180],"major":[31],"languages":[32,47],"such":[33],"as":[34],"English":[35],"and":[36,58,105,157,172,193],"Chinese,":[37],"not":[39,127],"thoroughly":[40],"investigated":[41],"low-resource":[43],"languages,":[44],"particularly":[45],"agglutinative":[46,63,82,123,196],"like":[48],"Mongolian,":[49],"due":[50],"to":[51,90,96,116,121],"scarcity":[53],"of":[54,61,141,147],"large-scale":[55,153],"data":[56,148],"resources":[57],"difficulty":[60],"understanding":[62],"knowledge.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,150],"propose":[69],"novel":[71,80],"PLM":[72,155],"for":[73,160],"Mongolian":[75,154],"language,":[76],"that":[77,101,164,185],"incorporates":[78],"three-stage":[81],"knowledge":[83,198],"injection":[84,88,109,126],"strategy.":[85],"Specifically,":[86],"early-stage":[87],"aims":[89],"convert":[91],"Mongolia":[93],"word":[94],"sequence":[95],"fine-grained":[98],"sub-word":[99],"token":[100],"comprises":[102],"stem":[104],"some":[106],"suffixes;":[107],"Middle-stage":[108],"designed":[110],"morphological":[112],"knowledge-based":[113],"masking":[114],"strategy":[115],"enhance":[117],"model's":[119],"ability":[120],"learn":[122],"knowledge;":[124],"Late-stage":[125],"only":[128],"involves":[129],"model":[131],"restoring":[132],"masked":[134],"tokens":[135],"but":[136],"also":[137],"predicting":[138],"order":[140],"suffixes.":[142],"To":[143],"address":[144],"issue":[146],"scarcity,":[149],"create":[151],"dataset":[156],"three":[158,161,181],"datasets":[159],"downstream":[162,182],"tasks,":[163],"are":[165],"News":[166],"Classification,":[167],"Name":[168],"Entity":[169],"Recognition":[170],"(NER),":[171],"Part-of-Speech":[173],"(POS)":[174],"prediction,":[175],"etc.":[176],"The":[177],"experimental":[178],"tasks":[183],"demonstrate":[184],"our":[186],"method":[187],"surpasses":[188],"traditional":[190],"approach":[192],"successfully":[194],"learns":[195],"Mongolian.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}