{"id":"https://openalex.org/W7140097181","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.38","title":"MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language","display_name":"MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140097181","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.38"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.loreslm-1.38","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.38","pdf_url":"https://aclanthology.org/2026.loreslm-1.38.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.loreslm-1.38.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121808733","display_name":"Sumit Yadav","orcid":"https://orcid.org/0009-0003-3988-0930","observed_orcids":["https://orcid.org/0009-0003-3988-0930","https://orcid.org/0009-0009-9984-2956"]},"institutions":[{"id":"https://openalex.org/I4210129773","display_name":"Institute of Engineering","ror":"https://ror.org/03ny67e60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773"]},{"id":"https://openalex.org/I4405263138","display_name":"Pulchowk Campus","ror":"https://ror.org/034bmrt60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Sumit Yadav","raw_affiliation_strings":["IOE , Pulchowk Campus , Lalitpur , Nepal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IOE , Pulchowk Campus , Lalitpur , Nepal","institution_ids":["https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104071667","display_name":"Raju Kumar Yadav","orcid":"https://orcid.org/0009-0009-4811-246X","observed_orcids":["https://orcid.org/0009-0009-4811-246X"]},"institutions":[{"id":"https://openalex.org/I4210129773","display_name":"Institute of Engineering","ror":"https://ror.org/03ny67e60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773"]},{"id":"https://openalex.org/I4405263138","display_name":"Pulchowk Campus","ror":"https://ror.org/034bmrt60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Raju Kumar Yadav","raw_affiliation_strings":["IOE , Pulchowk Campus , Lalitpur , Nepal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IOE , Pulchowk Campus , Lalitpur , Nepal","institution_ids":["https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120050542","display_name":"Utsav Maskey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Utsav Maskey","raw_affiliation_strings":["Macquarie University , Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University , Sydney , Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076626481","display_name":"Gautam Siddharth Kashyap","orcid":"https://orcid.org/0000-0003-2140-9617","observed_orcids":["https://orcid.org/0000-0003-2140-9617"]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gautam Siddharth Kashyap","raw_affiliation_strings":["Macquarie University , Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University , Sydney , Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041937508","display_name":"Ganesh Gautam","orcid":"https://orcid.org/0000-0002-1926-1492","observed_orcids":["https://orcid.org/0000-0002-1926-1492"]},"institutions":[{"id":"https://openalex.org/I4210129773","display_name":"Institute of Engineering","ror":"https://ror.org/03ny67e60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773"]},{"id":"https://openalex.org/I4405263138","display_name":"Pulchowk Campus","ror":"https://ror.org/034bmrt60","country_code":"NP","type":"education","lineage":["https://openalex.org/I155028946","https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}],"countries":["NP"],"is_corresponding":false,"raw_author_name":"Ganesh Gautam","raw_affiliation_strings":["IOE , Pulchowk Campus , Lalitpur , Nepal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IOE , Pulchowk Campus , Lalitpur , Nepal","institution_ids":["https://openalex.org/I4210129773","https://openalex.org/I4405263138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126968859","display_name":"Usman Naseem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["Macquarie University , Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University , Sydney , Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14379095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"444","last_page":"452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5303000211715698,"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":0.5303000211715698,"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":0.46140000224113464,"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":0.002099999925121665,"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/maithili-language","display_name":"Maithili language","score":0.925000011920929},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8790000081062317},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.6460000276565552},{"id":"https://openalex.org/keywords/multilingual-pretraining","display_name":"multilingual pre-training","score":0.5590000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6334999799728394},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5679000020027161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48919999599456787},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4733999967575073},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.3882000148296356},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C185954173","wikidata":"https://www.wikidata.org/wiki/Q4347052","display_name":"Object language","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.loreslm-1.38","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.38","pdf_url":"https://aclanthology.org/2026.loreslm-1.38.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.loreslm-1.38","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.38","pdf_url":"https://aclanthology.org/2026.loreslm-1.38.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5829595923423767,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140097181.pdf","grobid_xml":"https://content.openalex.org/works/W7140097181.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4287888679","https://openalex.org/W7160104624","https://openalex.org/W4401042205","https://openalex.org/W7140101172","https://openalex.org/W4411120413","https://openalex.org/W7140138356","https://openalex.org/W7140107760","https://openalex.org/W7140099571","https://openalex.org/W6885119379","https://openalex.org/W3118580427"],"abstract_inverted_index":{"Sumit":[0],"Yadav,":[1,4],"Raju":[2],"Kumar":[3],"Utsav":[5],"Maskey,":[6],"Gautam":[7],"Siddharth":[8],"Kashyap,":[9],"Ganesh":[10],"Gautam,":[11],"Usman":[12],"Naseem.":[13],"Proceedings":[14],"of":[15],"the":[16],"Second":[17],"Workshop":[18],"on":[19],"Language":[20],"Models":[21],"for":[22],"Low-Resource":[23],"Languages":[24],"(LoResLM":[25],"2026).":[26],"2026.":[27]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-06T00:00:00"}
