{"id":"https://openalex.org/W7134191562","doi":"https://doi.org/10.1109/bigdata66926.2025.11401059","title":"Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration","display_name":"Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134191562","doi":"https://doi.org/10.1109/bigdata66926.2025.11401059"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11401059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","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/A5014702176","display_name":"Kanchon Gharami","orcid":"https://orcid.org/0000-0003-0032-8201"},"institutions":[{"id":"https://openalex.org/I84475105","display_name":"Embry\u2013Riddle Aeronautical University","ror":"https://ror.org/010jskt71","country_code":"US","type":"education","lineage":["https://openalex.org/I84475105"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kanchon Gharami","raw_affiliation_strings":["Embry-Riddle Aeronautical University,Department of EECS,Daytona Beach,FL,USA"],"affiliations":[{"raw_affiliation_string":"Embry-Riddle Aeronautical University,Department of EECS,Daytona Beach,FL,USA","institution_ids":["https://openalex.org/I84475105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093219912","display_name":"Quazi Sarwar Muhtaseem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155759","display_name":"Merck (Singapore)","ror":"https://ror.org/05cq2am04","country_code":"SG","type":"company","lineage":["https://openalex.org/I4210155759"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Quazi Sarwar Muhtaseem","raw_affiliation_strings":["Hishab Singapore Pte. Ltd,NLP Engineering Team,Singapore"],"affiliations":[{"raw_affiliation_string":"Hishab Singapore Pte. Ltd,NLP Engineering Team,Singapore","institution_ids":["https://openalex.org/I4210155759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121038028","display_name":"Deepti Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I76756774","display_name":"Texas A&M University \u2013 Central Texas","ror":"https://ror.org/015hh0z25","country_code":"US","type":"education","lineage":["https://openalex.org/I76756774"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepti Gupta","raw_affiliation_strings":["Texas A&#x0026;M University - Central Texas,Department of Computer Information Systems,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Texas A&#x0026;M University - Central Texas,Department of Computer Information Systems,Texas,USA","institution_ids":["https://openalex.org/I76756774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047534464","display_name":"Lavanya Elluri","orcid":null},"institutions":[{"id":"https://openalex.org/I76756774","display_name":"Texas A&M University \u2013 Central Texas","ror":"https://ror.org/015hh0z25","country_code":"US","type":"education","lineage":["https://openalex.org/I76756774"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lavanya Elluri","raw_affiliation_strings":["Texas A&#x0026;M University - Central Texas,Department of Computer Information Systems,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Texas A&#x0026;M University - Central Texas,Department of Computer Information Systems,Texas,USA","institution_ids":["https://openalex.org/I76756774"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035634410","display_name":"Shafika Showkat Moni","orcid":"https://orcid.org/0000-0002-7710-4217"},"institutions":[{"id":"https://openalex.org/I84475105","display_name":"Embry\u2013Riddle Aeronautical University","ror":"https://ror.org/010jskt71","country_code":"US","type":"education","lineage":["https://openalex.org/I84475105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shafika Showkat Moni","raw_affiliation_strings":["Embry-Riddle Aeronautical University,Department of EECS,Daytona Beach,FL,USA"],"affiliations":[{"raw_affiliation_string":"Embry-Riddle Aeronautical University,Department of EECS,Daytona Beach,FL,USA","institution_ids":["https://openalex.org/I84475105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014702176"],"corresponding_institution_ids":["https://openalex.org/I84475105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88663021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6569","last_page":"6576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9257000088691711,"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":0.9257000088691711,"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":0.01549999974668026,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.009999999776482582,"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/hindi","display_name":"Hindi","score":0.6118999719619751},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.47749999165534973},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.29510000348091125},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.27129998803138733},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.2345000058412552}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6223999857902527},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6057000160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552299976348877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48350000381469727},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.2345000058412552},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.23250000178813934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11401059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","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":27,"referenced_works":["https://openalex.org/W2012070276","https://openalex.org/W2139645402","https://openalex.org/W2139671364","https://openalex.org/W2151952699","https://openalex.org/W2278252977","https://openalex.org/W2281234840","https://openalex.org/W2805866690","https://openalex.org/W2908842079","https://openalex.org/W2950599942","https://openalex.org/W2963250244","https://openalex.org/W2964343359","https://openalex.org/W4205470886","https://openalex.org/W4210361776","https://openalex.org/W4226016777","https://openalex.org/W4318002233","https://openalex.org/W4385245566","https://openalex.org/W4386566460","https://openalex.org/W4391017630","https://openalex.org/W4394570045","https://openalex.org/W4396789590","https://openalex.org/W4402670856","https://openalex.org/W4404577135","https://openalex.org/W4404781071","https://openalex.org/W4411120000","https://openalex.org/W4412378006","https://openalex.org/W7131778213","https://openalex.org/W7133321304"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-09T07:06:17.341095","created_date":"2026-03-09T00:00:00"}
