{"id":"https://openalex.org/W4412889175","doi":"https://doi.org/10.18653/v1/2025.bea-1.20","title":"LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages","display_name":"LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889175","doi":"https://doi.org/10.18653/v1/2025.bea-1.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.20","pdf_url":"https://aclanthology.org/2025.bea-1.20.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071113381","display_name":"N J Karthika","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karthika N J","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111208108","display_name":"Krishnakant Bhatt","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishnakant Bhatt","raw_affiliation_strings":["Indian Institute of Technology Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089606464","display_name":"Ganesh Ramakrishnan","orcid":"https://orcid.org/0000-0003-4533-2490"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh Ramakrishnan","raw_affiliation_strings":["Indian Institute of Technology Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Indian Institute of Technology Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14557741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9732999801635742,"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"}},{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.9362999796867371,"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/sanskrit","display_name":"Sanskrit","score":0.9362583756446838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628819942474365},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6725682020187378},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5541099905967712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47004714608192444},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30199772119522095},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04581150412559509}],"concepts":[{"id":"https://openalex.org/C29912816","wikidata":"https://www.wikidata.org/wiki/Q11059","display_name":"Sanskrit","level":2,"score":0.9362583756446838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628819942474365},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6725682020187378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5541099905967712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47004714608192444},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30199772119522095},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04581150412559509}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.20","pdf_url":"https://aclanthology.org/2025.bea-1.20.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.20","pdf_url":"https://aclanthology.org/2025.bea-1.20.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323448","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889175.pdf","grobid_xml":"https://content.openalex.org/works/W4412889175.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2802427415","https://openalex.org/W2620810496","https://openalex.org/W4210574062","https://openalex.org/W4206712636","https://openalex.org/W2064780833","https://openalex.org/W2315373242","https://openalex.org/W4382808597","https://openalex.org/W4385471946","https://openalex.org/W1967221745","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Translating":[0],"technical":[1,93,121,152],"terms":[2,122],"into":[3],"lexically":[4],"similar,":[5],"low-resource":[6],"Indian":[7,142],"languages":[8],"remains":[9],"a":[10,24,65,108],"challenge":[11],"due":[12],"to":[13,50,113],"limited":[14],"parallel":[15],"data":[16],"and":[17,40,58,80,101,147,158],"the":[18,76,115,119,131,145,162],"complexity":[19],"of":[20,27,34,78,118,151],"linguistic":[21],"structures.We":[22],"propose":[23],"novel":[25],"use-case":[26],"Sanskrit-based":[28],"segments":[29],"for":[30,69,92,130,165],"linguistically":[31,148],"informed":[32],"translation":[33,95,150],"such":[35],"terms,":[36],"leveraging":[37],"subword-level":[38],"similarity":[39],"morphological":[41],"alignment":[42],"across":[43],"related":[44],"languages.Our":[45],"approach":[46,155],"uses":[47],"character-level":[48],"segmentation":[49],"identify":[51],"meaningful":[52],"subword":[53],"units,":[54],"facilitating":[55],"more":[56],"accurate":[57,146],"contextaware":[59],"translation.To":[60],"enable":[61],"this,":[62],"we":[63,106],"utilize":[64],"Character-level":[66],"Transformer":[67],"model":[68],"Sanskrit":[70],"Word":[71],"Segmentation":[72],"(CharSS),":[73],"which":[74],"addresses":[75],"complexities":[77],"sandhi":[79],"morphophonemic":[81],"changes":[82],"during":[83],"segmentation.We":[84],"observe":[85],"consistent":[86],"improvements":[87],"in":[88,135,141,160,167],"two":[89],"experimental":[90],"settings":[91],"term":[94],"using":[96,123],"Sanskrit-derived":[97],"segments,":[98],"averaging":[99],"8.46":[100],"6.79":[102],"chrF++":[103],"scores,":[104],"respectively.Further,":[105],"conduct":[107],"post":[109],"hoc":[110],"human":[111],"evaluation":[112],"verify":[114],"quality":[116],"assessment":[117],"translated":[120],"automated":[124],"metrics.This":[125],"work":[126],"has":[127],"important":[128],"implications":[129],"education":[132],"field,":[133],"especially":[134],"creating":[136],"accessible,":[137],"high-quality":[138],"learning":[139],"materials":[140],"languages.By":[143],"supporting":[144],"rooted":[149],"content,":[153],"our":[154],"facilitates":[156],"inclusivity":[157],"aids":[159],"bridging":[161],"resource":[163],"gap":[164],"learners":[166],"lowresource":[168],"language":[169],"communities.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}