{"id":"https://openalex.org/W4393406262","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482976","title":"Efficiently Transferring Pre-trained Language Model RoBERTa Base English to Hindi Using WECHSEL","display_name":"Efficiently Transferring Pre-trained Language Model RoBERTa Base English to Hindi Using WECHSEL","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406262","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482976"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482976","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5024926698","display_name":"Ramesh K. Bhukya","orcid":"https://orcid.org/0000-0002-6221-5627"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramesh K. Bhukya","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Electronics and Communication Engineering,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Electronics and Communication Engineering,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026058891","display_name":"Anjali Chaturvedi","orcid":"https://orcid.org/0000-0002-1224-7073"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anjali Chaturvedi","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Electronics and Communication Engineering,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Electronics and Communication Engineering,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108913418","display_name":"Hardik Bajaj","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik Bajaj","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113157814","display_name":"Udgam Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Udgam Shah","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002585659","display_name":"Sumit Singh","orcid":"https://orcid.org/0000-0002-3292-4131"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Singh","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060052491","display_name":"Uma Shanker Tiwary","orcid":"https://orcid.org/0000-0001-7206-9013"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Uma Shanker Tiwary","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad,Department of Information Technology,Prayagraj,Uttar Pradesh,India,211015","institution_ids":["https://openalex.org/I26072440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26072440"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2133939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9685999751091003,"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":0.9685999751091003,"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":0.6657760739326477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6605064868927002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6304121017456055},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.5530755519866943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541588306427002},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38944312930107117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13282006978988647},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07505196332931519}],"concepts":[{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6657760739326477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6605064868927002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6304121017456055},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5530755519866943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541588306427002},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38944312930107117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13282006978988647},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07505196332931519},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482976","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2294774419","https://openalex.org/W2747680751","https://openalex.org/W2896457183","https://openalex.org/W2952638691","https://openalex.org/W2963002901","https://openalex.org/W2963088995","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W2995549860","https://openalex.org/W3034469191","https://openalex.org/W3035390927","https://openalex.org/W3112784227","https://openalex.org/W3128376221","https://openalex.org/W3192478068","https://openalex.org/W3212990991","https://openalex.org/W4214867578","https://openalex.org/W4287888698","https://openalex.org/W4287889470","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6772253010"],"related_works":["https://openalex.org/W2384553807","https://openalex.org/W1557888283","https://openalex.org/W3089999372","https://openalex.org/W2265245145","https://openalex.org/W3110423299","https://openalex.org/W4312229285","https://openalex.org/W2738278463","https://openalex.org/W4308939443","https://openalex.org/W4299528489","https://openalex.org/W3204019825"],"abstract_inverted_index":{"A":[0],"crucial":[1],"element":[2],"of":[3,48,67,137,148,192,200],"Natural":[4],"Language":[5,21],"Processing":[6],"(NLP)":[7],"is":[8,65,125,176,195],"to":[9,15,79,101,112,156],"make":[10],"it":[11],"possible":[12],"for":[13,45,55,140],"computers":[14],"comprehend":[16],"and":[17,40,62,116,173],"process":[18],"human":[19],"language,":[20,133],"models":[22,35,88,147],"(LMs),":[23],"have":[24,41],"taken":[25],"over":[26],"the":[27,68,106,113,131,174,198,201],"discipline":[28],"in":[29,59,89,130],"recent":[30],"years.":[31],"LMs":[32,74],"are":[33],"pre-trained":[34,73],"that":[36,143],"can":[37],"be":[38],"customized":[39],"significantly":[42],"improved":[43],"performance":[44],"a":[46,96,128],"variety":[47],"challenging":[49],"natural":[50],"language":[51],"tasks.":[52],"Bidirectional":[53],"Encoders":[54],"Transformers":[56],"(BERT)":[57],"used":[58,95],"both":[60],"English":[61,82,123],"other":[63,90,146,180],"languages,":[64],"one":[66],"most":[69],"well-known":[70],"LMs.":[71],"Large":[72],"require":[75],"enormous":[76],"computational":[77],"resources":[78],"train":[80],"on":[81,105,167],"text.":[83],"This":[84,93],"makes":[85],"training":[86,160],"these":[87],"languages":[91],"difficult.":[92],"paper":[94],"unique":[97],"approach":[98,139],"termed":[99],"WECHSEL":[100,110,144,162,186],"address":[102],"this":[103,138,184],"problem":[104],"Hindi":[107,141,164,188],"dataset.":[108],"The":[109,120,135],"method":[111],"RoBERTa":[114],"model":[115],"assess":[117],"its":[118],"effectiveness.":[119],"source":[121],"model\u2019s":[122],"tokenizer":[124,129],"replaced":[126],"with":[127,154],"target":[132],"Hindi.":[134],"advantages":[136],"demonstrate":[142],"outperforms":[145],"comparable":[149],"size":[150],"built":[151],"from":[152],"scratch":[153],"up":[155],"64":[157],"times":[158],"less":[159],"effort.":[161],"RoBERTa-based":[163,187],"was":[165],"fine-tuned":[166],"NER":[168],"task":[169],"using":[170],"SemEval-2022":[171],"datasets,":[172],"accuracy":[175,191],"greater":[177],"than":[178,197],"any":[179],"BERT-based":[181],"models.":[182,205],"In":[183],"paper,":[185],"achieved":[189],"an":[190],"73.45%,":[193],"which":[194],"higher":[196],"rest":[199],"Hindi-language":[202],"based":[203],"BERT":[204]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}