{"id":"https://openalex.org/W3197314979","doi":null,"title":"IndicBART: A Pre-trained Model for Natural Language Generation of Indic Languages.","display_name":"IndicBART: A Pre-trained Model for Natural Language Generation of Indic Languages.","publication_year":2021,"publication_date":"2021-09-07","ids":{"openalex":"https://openalex.org/W3197314979","mag":"3197314979"},"language":"en","primary_location":{"id":"mag:3197314979","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02903","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2109.02903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421","observed_orcids":["https://orcid.org/0000-0003-0664-3421"]},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY"],"raw_orcid":"https://orcid.org/0000-0003-0664-3421","affiliations":[{"raw_affiliation_string":"NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054442548","display_name":"Himani Shrotriya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himani Shrotriya","raw_affiliation_strings":["Indian Institute of Technology  Madras"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology  Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052909911","display_name":"Anoop Kunchukuttan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anoop Kunchukuttan","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069271622","display_name":"Ratish Puduppully","orcid":"https://orcid.org/0009-0001-0857-2842","observed_orcids":["https://orcid.org/0009-0001-0857-2842"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ratish Puduppully","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":"https://orcid.org/0009-0001-0857-2842","affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050036814","display_name":"Mitesh M. Khapra","orcid":"https://orcid.org/0009-0008-3687-9922","observed_orcids":["https://orcid.org/0009-0008-3687-9922"]},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mitesh M. Khapra","raw_affiliation_strings":["Indian Institute of Technology  Madras"],"raw_orcid":"https://orcid.org/0009-0008-3687-9922","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology  Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101614266","display_name":"Pratyush Kumar","orcid":"https://orcid.org/0000-0002-8732-0183","observed_orcids":["https://orcid.org/0000-0002-8732-0183","https://orcid.org/0000-0002-7446-0363"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratyush Kumar","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":"https://orcid.org/0000-0002-8732-0183","affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"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/T10028","display_name":"Topic Modeling","score":0.5990999937057495,"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/T10028","display_name":"Topic Modeling","score":0.5990999937057495,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3928000032901764,"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":0.0027000000700354576,"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/indo-aryan-languages","display_name":"Indo-Aryan languages","score":0.9259999990463257},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"natural language generation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/sequence-to-sequence-models","display_name":"sequence-to-sequence models","score":0.7850000262260437},{"id":"https://openalex.org/keywords/neural-machine-translation","display_name":"neural machine translation","score":0.777999997138977},{"id":"https://openalex.org/keywords/devanagari","display_name":"Devanagari script","score":0.9539999961853027},{"id":"https://openalex.org/keywords/orthographic-similarity","display_name":"orthographic similarity","score":0.8889999985694885},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.800000011920929},{"id":"https://openalex.org/keywords/multilingual-fine-tuning","display_name":"multilingual fine-tuning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039548993110657},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7600666284561157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6713314652442932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6542648673057556},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.609919011592865},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5685587525367737},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.5255419611930847},{"id":"https://openalex.org/C2780144916","wikidata":"https://www.wikidata.org/wiki/Q38592","display_name":"Devanagari","level":4,"score":0.5175063610076904},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4927807152271271},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43988150358200073},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4293597340583801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3129982054233551},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13972049951553345},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3197314979","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02903","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3197314979","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02903","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2229833550","https://openalex.org/W2337363174","https://openalex.org/W2525778437","https://openalex.org/W2612675303","https://openalex.org/W2744813330","https://openalex.org/W2752630748","https://openalex.org/W2759088880","https://openalex.org/W2766182427","https://openalex.org/W2798362442","https://openalex.org/W2809687772","https://openalex.org/W2885185669","https://openalex.org/W2888482885","https://openalex.org/W2889511806","https://openalex.org/W2897105542","https://openalex.org/W2905933322","https://openalex.org/W2919290281","https://openalex.org/W2945415576","https://openalex.org/W2963216553","https://openalex.org/W2963341956","https://openalex.org/W2963592583","https://openalex.org/W2963768805","https://openalex.org/W2964007535","https://openalex.org/W2964910501","https://openalex.org/W2970316683","https://openalex.org/W2978922291","https://openalex.org/W2982399380","https://openalex.org/W2983040767","https://openalex.org/W2985301125","https://openalex.org/W3000965575","https://openalex.org/W3001434439","https://openalex.org/W3012541776","https://openalex.org/W3031586918","https://openalex.org/W3046368065","https://openalex.org/W3099919888","https://openalex.org/W3115264425","https://openalex.org/W3118415754","https://openalex.org/W3166656494","https://openalex.org/W3169483174","https://openalex.org/W3173360659","https://openalex.org/W4287020707","https://openalex.org/W6893675597"],"related_works":["https://openalex.org/W4285255685","https://openalex.org/W4311550865","https://openalex.org/W4385572860","https://openalex.org/W4385574330","https://openalex.org/W4361806844","https://openalex.org/W7223059137","https://openalex.org/W3185416692","https://openalex.org/W4287887882","https://openalex.org/W4408794147","https://openalex.org/W3099919888"],"abstract_inverted_index":{"In":[0],"this":[1,117],"paper":[2],"we":[3],"present":[4],"IndicBART,":[5],"a":[6],"multilingual,":[7],"sequence-to-sequence":[8],"pre-trained":[9,21],"model":[10,109],"focusing":[11],"on":[12,42,55,88,103],"11":[13],"Indic":[14,29,37],"languages":[15,66],"and":[16,50,61],"English.":[17],"Different":[18],"from":[19],"existing":[20],"models,":[22],"IndicBART":[23,41,72,108],"utilizes":[24],"the":[25,90,104,113],"orthographic":[26],"similarity":[27],"between":[28,35],"scripts":[30],"to":[31],"improve":[32],"transfer":[33],"learning":[34],"similar":[36],"languages.":[38],"We":[39],"evaluate":[40],"two":[43],"NLG":[44],"tasks:":[45],"Neural":[46],"Machine":[47],"Translation":[48],"(NMT)":[49],"extreme":[51,62],"summarization.":[52],"Our":[53,85],"experiments":[54],"NMT":[56],"for":[57,64],"12":[58],"language":[59],"pairs":[60],"summarization":[63],"7":[65],"using":[67],"multilingual":[68],"fine-tuning":[69],"show":[70],"that":[71],"is":[73,110],"competitive":[74],"with":[75],"or":[76],"better":[77],"than":[78],"mBART50":[79],"despite":[80],"containing":[81],"significantly":[82],"fewer":[83],"parameters.":[84],"analyses":[86],"focus":[87],"identifying":[89],"impact":[91],"of":[92],"script":[93],"unification":[94],"(to":[95],"Devanagari),":[96],"corpora":[97],"size":[98],"as":[99,101],"well":[100],"multilingualism":[102],"final":[105],"performance.":[106],"The":[107],"available":[111],"under":[112],"MIT":[114],"license":[115],"at":[116],"https":[118],"URL":[119],".":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-09-13T00:00:00"}