{"id":"https://openalex.org/W7137907717","doi":"https://doi.org/10.18653/v1/2025.findings-ijcnlp.142","title":"Regional-TinyStories: A Small Language Model Framework for Evaluating Language Learning, Tokenizers, and Datasets","display_name":"Regional-TinyStories: A Small Language Model Framework for Evaluating Language Learning, Tokenizers, and Datasets","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7137907717","doi":"https://doi.org/10.18653/v1/2025.findings-ijcnlp.142"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-ijcnlp.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-ijcnlp.142","pdf_url":"https://aclanthology.org/2025.findings-ijcnlp.142.pdf","source":null,"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 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-ijcnlp.142.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126331508","display_name":"Nirvan Patil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nirvan Patil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704865","display_name":"Malhar Abhay Inamdar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malhar Abhay Inamdar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031686351","display_name":"Agnivo Gosai","orcid":"https://orcid.org/0000-0002-5146-509X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agnivo Gosai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126359849","display_name":"Guruprasad Pathak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guruprasad Pathak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704776","display_name":"Anish Joshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anish Joshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126295099","display_name":"Anish Joshirao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anish Joshirao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021661240","display_name":"Raj Dandekar","orcid":"https://orcid.org/0000-0003-1946-0667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raj Dandekar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109819059","display_name":"Rajat Dandekar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat Dandekar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034707872","display_name":"Sreedath Panat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreedath Panat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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":0.82982598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2318","last_page":"2367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3937999904155731,"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":0.3937999904155731,"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":0.06849999725818634,"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/T13629","display_name":"Text Readability and Simplification","score":0.046799998730421066,"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/language-model","display_name":"Language model","score":0.4832000136375427},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.42340001463890076},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.358599990606308},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3197999894618988},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29809999465942383},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2745000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.42340001463890076},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2547999918460846},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-ijcnlp.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-ijcnlp.142","pdf_url":"https://aclanthology.org/2025.findings-ijcnlp.142.pdf","source":null,"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 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-ijcnlp.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-ijcnlp.142","pdf_url":"https://aclanthology.org/2025.findings-ijcnlp.142.pdf","source":null,"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 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6430853605270386}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137907717.pdf","grobid_xml":"https://content.openalex.org/works/W7137907717.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nirvan":[0],"Patil,":[1],"Malhar":[2],"Abhay":[3],"Inamdar,":[4],"Agnivo":[5],"Gosai,":[6],"Guruprasad":[7],"Pathak,":[8],"Anish":[9,11],"Joshi,":[10],"Joshirao,":[12],"Raj":[13],"Dandekar,":[14,16],"Rajat":[15],"Sreedath":[17],"Panat.":[18],"Proceedings":[19],"of":[20,34,38],"the":[21,31,35,39],"14th":[22],"International":[23],"Joint":[24],"Conference":[25,33],"on":[26],"Natural":[27],"Language":[28],"Processing":[29],"and":[30],"4th":[32],"Asia-Pacific":[36],"Chapter":[37],"Association":[40],"for":[41],"Computational":[42],"Linguistics.":[43],"2025.":[44]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
