{"id":"https://openalex.org/W4416256151","doi":"https://doi.org/10.48550/arxiv.2509.19941","title":"CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems","display_name":"CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W4416256151","doi":"https://doi.org/10.48550/arxiv.2509.19941"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.19941","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19941","pdf_url":"https://arxiv.org/pdf/2509.19941","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.19941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056774341","display_name":"Soham Bhattacharjee","orcid":"https://orcid.org/0009-0008-2828-3088","observed_orcids":["https://orcid.org/0009-0008-2828-3088"]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhattacharjee, Soham","raw_affiliation_strings":["Department of Computer Science and Engineering , Indian Institute of Technology Patna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009926678","display_name":"Mukund Kumar Roy","orcid":"https://orcid.org/0000-0001-6000-0334","observed_orcids":["https://orcid.org/0000-0001-6000-0334"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy, Mukund K","raw_affiliation_strings":["SNLP Lab , CDAC Noida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SNLP Lab , CDAC Noida","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117932523","display_name":"Yathish Poojary","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Poojary, Yathish","raw_affiliation_strings":["Department of Computer Science and Engineering , Manipal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Manipal Institute of Technology","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012548633","display_name":"Bhargav Dave","orcid":"https://orcid.org/0000-0003-2742-480X","observed_orcids":["https://orcid.org/0000-0003-2742-480X"]},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dave, Bhargav","raw_affiliation_strings":["Department of Computer Science and Engineering , Dhirubhai Ambani University , Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Dhirubhai Ambani University , Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062387277","display_name":"M Rahul Raj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210097016","display_name":"International Institute of Information Technology","ror":"https://ror.org/00qryer39","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097016"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raj, Mihir","raw_affiliation_strings":["Department of CSE , IIIT Bhubaneshwar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , IIIT Bhubaneshwar","institution_ids":["https://openalex.org/I4210097016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090125308","display_name":"Vandan Mujadia","orcid":"https://orcid.org/0000-0002-7823-8014","observed_orcids":["https://orcid.org/0000-0002-7823-8014"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mujadia, Vandan","raw_affiliation_strings":["LTRC , IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC , IIIT Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069541957","display_name":"Baban Gain","orcid":"https://orcid.org/0000-0001-8673-7078","observed_orcids":["https://orcid.org/0000-0001-8673-7078"]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gain, Baban","raw_affiliation_strings":["Department of Computer Science and Engineering , Indian Institute of Technology Patna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019439792","display_name":"Pruthwik Mishra","orcid":"https://orcid.org/0009-0000-3657-5250","observed_orcids":["https://orcid.org/0009-0000-3657-5250"]},"institutions":[{"id":"https://openalex.org/I42014448","display_name":"Sardar Vallabhbhai National Institute of Technology Surat","ror":"https://ror.org/02y394t43","country_code":"IN","type":"education","lineage":["https://openalex.org/I42014448"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mishra, Pruthwik","raw_affiliation_strings":["Department of AI , SVNIT , Surat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI , SVNIT , Surat","institution_ids":["https://openalex.org/I42014448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055904645","display_name":"Arafat Ahsan","orcid":"https://orcid.org/0009-0009-9709-3832","observed_orcids":["https://orcid.org/0009-0009-9709-3832"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ahsan, Arafat","raw_affiliation_strings":["LTRC , IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC , IIIT Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023102557","display_name":"Parameswari Krishnamurthy","orcid":"https://orcid.org/0000-0002-9014-4993","observed_orcids":["https://orcid.org/0000-0002-9014-4993"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishnamurthy, Parameswari","raw_affiliation_strings":["LTRC , IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC , IIIT Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112333661","display_name":"Ashwath Rao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rao, Ashwath","raw_affiliation_strings":["Department of Computer Science and Engineering , Manipal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Manipal Institute of Technology","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011172652","display_name":"Gurpreet Singh Josan","orcid":"https://orcid.org/0000-0002-3195-2229","observed_orcids":["https://orcid.org/0000-0002-3195-2229"]},"institutions":[{"id":"https://openalex.org/I79161377","display_name":"Punjabi University","ror":"https://ror.org/00xdn8y92","country_code":"IN","type":"education","lineage":["https://openalex.org/I79161377"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Josan, Gurpreet Singh","raw_affiliation_strings":["Department of CSE , Punjabi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , Punjabi University","institution_ids":["https://openalex.org/I79161377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071139892","display_name":"Preeti Dubey","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dubey, Preeti","raw_affiliation_strings":["Department of CSE , Govt. College for Women Jammu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , Govt. College for Women Jammu","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025392172","display_name":"Aadil Amin Kak","orcid":"https://orcid.org/0009-0002-7663-5531","observed_orcids":["https://orcid.org/0009-0002-7663-5531"]},"institutions":[{"id":"https://openalex.org/I135388327","display_name":"University of Kashmir","ror":"https://ror.org/032xfst36","country_code":"IN","type":"education","lineage":["https://openalex.org/I135388327"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kak, Aadil Amin","raw_affiliation_strings":["Department of Linguistics , University of Kashmir 10 VLSI Design Group , CDAC Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics , University of Kashmir 10 VLSI Design Group , CDAC Bangalore","institution_ids":["https://openalex.org/I135388327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kulkarni, Anna Rao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kulkarni, Anna Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024894834","display_name":"Narendra VG","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"VG, Narendra","raw_affiliation_strings":["Department of Computer Science and Engineering , Manipal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Manipal Institute of Technology","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074671737","display_name":"Sunita Arora","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arora, Sunita","raw_affiliation_strings":["SNLP Lab , CDAC Noida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SNLP Lab , CDAC Noida","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120450849","display_name":"Rakesh Balbantray","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210097016","display_name":"International Institute of Information Technology","ror":"https://ror.org/00qryer39","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097016"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balbantray, Rakesh","raw_affiliation_strings":["Department of CSE , IIIT Bhubaneshwar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , IIIT Bhubaneshwar","institution_ids":["https://openalex.org/I4210097016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Majumdar, Prasenjit","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Majumdar, Prasenjit","raw_affiliation_strings":["Department of Computer Science and Engineering , Dhirubhai Ambani University , Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Dhirubhai Ambani University , Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arora, Karunesh K","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arora, Karunesh K","raw_affiliation_strings":["SNLP Lab , CDAC Noida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SNLP Lab , CDAC Noida","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834","observed_orcids":["https://orcid.org/0000-0003-3612-8834"]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ekbal, Asif","raw_affiliation_strings":["Department of Computer Science and Engineering , Indian Institute of Technology Patna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043725569","display_name":"Dipti Mishra Sharma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharma, Dipti Mishra","raw_affiliation_strings":["LTRC , IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC , IIIT Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9961000084877014,"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":0.9961000084877014,"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":0.002099999925121665,"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"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/indian-languages","display_name":"Indian languages","score":0.7570000290870667},{"id":"https://openalex.org/keywords/multilingual-machine-translation","display_name":"multilingual machine translation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.824999988079071},{"id":"https://openalex.org/keywords/indic-scripts","display_name":"Indic scripts","score":0.6069999933242798},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.652999997138977},{"id":"https://openalex.org/keywords/health-domain","display_name":"health domain","score":0.9660000205039978},{"id":"https://openalex.org/keywords/nllb","display_name":"NLLB","score":0.5929999947547913},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.5230000019073486},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.6259999871253967},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.7450000047683716},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu language","score":0.6330000162124634},{"id":"https://openalex.org/keywords/kashmiri","display_name":"Kashmiri","score":0.6069999933242798},{"id":"https://openalex.org/keywords/sindhi","display_name":"Sindhi","score":0.7900000214576721},{"id":"https://openalex.org/keywords/kannada","display_name":"Kannada language","score":0.550000011920929},{"id":"https://openalex.org/keywords/gujarati","display_name":"Gujarati","score":0.671999990940094},{"id":"https://openalex.org/keywords/odia","display_name":"Odia","score":0.6850000023841858},{"id":"https://openalex.org/keywords/punjabi","display_name":"Punjabi language","score":0.859000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202000260353088},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6909000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273999810218811},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.559499979019165},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C2779296024","wikidata":"https://www.wikidata.org/wiki/Q5137","display_name":"Gujarati","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.3781999945640564},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3472999930381775},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2727000117301941}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.19941","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19941","pdf_url":"https://arxiv.org/pdf/2509.19941","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.19941","doi":"https://doi.org/10.48550/arxiv.2509.19941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19941","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.19941","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19941","pdf_url":"https://arxiv.org/pdf/2509.19941","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416256151.pdf","grobid_xml":"https://content.openalex.org/works/W4416256151.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3031586918","https://openalex.org/W4378505287"],"related_works":["https://openalex.org/W7214298275","https://openalex.org/W7160616697","https://openalex.org/W4405095498","https://openalex.org/W4378505287","https://openalex.org/W3031586918","https://openalex.org/W3000965575","https://openalex.org/W7119224458","https://openalex.org/W4405354851","https://openalex.org/W7202246355","https://openalex.org/W4414160899"],"abstract_inverted_index":{"India's":[0],"linguistic":[1],"landscape":[2],"is":[3,93],"one":[4],"of":[5,67,86,122,218],"the":[6,10,30,120,152,161,216,231],"most":[7],"diverse":[8],"in":[9,29,36,155],"world,":[11],"comprising":[12,83],"over":[13],"120":[14],"major":[15],"languages":[16,28,47,69,224],"and":[17,81,96,105,113,124,133,142,150,203,225],"approximately":[18],"1,600":[19],"additional":[20],"languages,":[21],"with":[22,171],"22":[23],"officially":[24],"recognized":[25],"as":[26],"scheduled":[27],"Indian":[31,46,223],"Constitution.":[32],"Despite":[33],"recent":[34],"progress":[35],"multilingual":[37,173],"neural":[38],"machine":[39,110,232],"translation":[40,111,233],"(NMT),":[41],"high-quality":[42,61,219],"parallel":[43,63],"corpora":[44],"for":[45,128,222,230],"remain":[48],"scarce,":[49],"especially":[50],"across":[51],"varied":[52],"domains.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,131,211],"introduce":[58],"a":[59,84,193,227],"large-scale,":[60],"annotated":[62],"corpus":[64],"covering":[65],"11":[66],"these":[68],":":[70],"English,":[71],"Telugu,":[72],"Hindi,":[73],"Punjabi,":[74],"Odia,":[75],"Kashmiri,":[76],"Sindhi,":[77],"Dogri,":[78],"Kannada,":[79],"Urdu,":[80],"Gujarati":[82],"total":[85],"772,000":[87],"bi-text":[88],"sentence":[89],"pairs.":[90],"The":[91],"dataset":[92],"carefully":[94],"curated":[95],"systematically":[97],"categorized":[98],"into":[99,200],"three":[100],"key":[101],"domains:":[102],"Government,":[103],"Health,":[104],"General,":[106],"to":[107,213],"enable":[108],"domain-aware":[109],"research":[112,234],"facilitate":[114],"effective":[115],"domain":[116,201],"adaptation.":[117],"To":[118],"demonstrate":[119],"utility":[121],"CorIL":[123],"establish":[125],"strong":[126],"benchmarks":[127],"future":[129],"research,":[130],"fine-tune":[132],"evaluate":[134],"several":[135],"state-of-the-art":[136],"NMT":[137],"models,":[138],"including":[139],"IndicTrans2,":[140],"NLLB,":[141],"BhashaVerse.":[143],"Our":[144],"analysis":[145],"reveals":[146],"important":[147],"performance":[148,165,196],"trends":[149],"highlights":[151],"corpus's":[153],"value":[154],"probing":[156],"model":[157],"capabilities.":[158],"For":[159],"instance,":[160],"results":[162],"show":[163],"distinct":[164],"patterns":[166],"based":[167],"on":[168,178,187],"language":[169],"script,":[170],"massively":[172],"models":[174,185],"showing":[175],"an":[176],"advantage":[177],"Perso-Arabic":[179],"scripts":[180],"(Urdu,":[181],"Sindhi)":[182],"while":[183],"other":[184],"excel":[186],"Indic":[188],"scripts.":[189],"This":[190],"paper":[191],"provides":[192],"detailed":[194],"domain-wise":[195],"analysis,":[197],"offering":[198],"insights":[199],"sensitivity":[202],"cross-script":[204],"transfer":[205],"learning.":[206],"By":[207],"publicly":[208],"releasing":[209],"CorIL,":[210],"aim":[212],"significantly":[214],"improve":[215],"availability":[217],"training":[220],"data":[221],"provide":[226],"valuable":[228],"resource":[229],"community.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
