{"id":"https://openalex.org/W7166874302","doi":"https://doi.org/10.18653/v1/2026.acl-long.551","title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","display_name":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166874302","doi":"https://doi.org/10.18653/v1/2026.acl-long.551"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.551","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.551","pdf_url":"https://aclanthology.org/2026.acl-long.551.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.551.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139839456","display_name":"Raghvendra Kumar","orcid":null},"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":"Raghvendra Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering , Indian Institute of Technology Patna , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Indian Institute of Technology Patna , India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139753032","display_name":"Devankar Raj","orcid":null},"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":"Devankar Raj","raw_affiliation_strings":["Indian Institute of Technology Patna , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna , India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139736607","display_name":"Sriparna Saha","orcid":null},"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":"Sriparna Saha","raw_affiliation_strings":["Department of Computer Science and Engineering , Indian Institute of Technology Patna , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Indian Institute of Technology Patna , India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83956662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11998","last_page":"12064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.635699987411499,"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":0.635699987411499,"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":0.11919999867677689,"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":0.039400000125169754,"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/feature","display_name":"Feature (linguistics)","score":0.28139999508857727},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.25690001249313354},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.23680000007152557},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.23510000109672546},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.23090000450611115}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6046000123023987},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23680000007152557},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.23510000109672546},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.23090000450611115},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.21819999814033508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.551","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.551","pdf_url":"https://aclanthology.org/2026.acl-long.551.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.551","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.551","pdf_url":"https://aclanthology.org/2026.acl-long.551.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166874302.pdf","grobid_xml":"https://content.openalex.org/works/W7166874302.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"India's":[0],"linguistic":[1,92,140],"landscape,":[2],"spanning":[3],"22":[4],"scheduled":[5],"languages":[6,40,44],"and":[7,20,53,75,79,85,95,102,105,118,121,133],"hundreds":[8],"of":[9,51,66],"marginalized":[10],"dialects,":[11],"has":[12],"driven":[13],"rapid":[14],"growth":[15],"in":[16,99,137],"NLP":[17,68,135],"datasets,":[18,72],"benchmarks,":[19,74],"pretrained":[21],"models.However,":[22],"no":[23],"dedicated":[24],"survey":[25,65,124],"consolidates":[26],"resources":[27,90],"developed":[28],"specifically":[29],"for":[30,129],"Indian":[31,43,67,139],"languages.Existing":[32],"reviews":[33],"either":[34],"focus":[35],"on":[36],"a":[37,126],"few":[38],"high-resource":[39],"or":[41],"subsume":[42],"within":[45],"broader":[46],"multilingual":[47],"settings,":[48],"limiting":[49],"coverage":[50],"low-resource":[52],"culturally":[54,86,131],"diverse":[55],"varieties.To":[56],"address":[57],"this":[58],"gap,":[59],"we":[60],"present":[61],"the":[62,138],"first":[63],"unified":[64],"resources,":[69],"covering":[70],"200+":[71],"50+":[73],"100+":[76],"models,":[77],"tools,":[78],"systems":[80],"across":[81],"text,":[82],"speech,":[83],"multimodal,":[84],"grounded":[87],"tasks.We":[88],"organize":[89],"by":[91],"phenomena,":[93],"domains,":[94],"modalities;":[96],"analyze":[97],"trends":[98],"annotation,":[100],"evaluation,":[101],"model":[103],"design;":[104],"identify":[106],"persistent":[107],"challenges":[108],"such":[109],"as":[110],"data":[111],"sparsity,":[112],"uneven":[113],"language":[114],"coverage,":[115],"script":[116],"diversity,":[117],"limited":[119],"cultural":[120],"domain":[122],"generalization.This":[123],"offers":[125],"consolidated":[127],"foundation":[128],"equitable,":[130],"grounded,":[132],"scalable":[134],"research":[136],"ecosystem.":[141]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}