{"id":"https://openalex.org/W4285211844","doi":"https://doi.org/10.18653/v1/2022.acl-long.18","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","display_name":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285211844","doi":"https://doi.org/10.18653/v1/2022.acl-long.18"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.acl-long.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.18","pdf_url":"https://aclanthology.org/2022.acl-long.18.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th 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":"hybrid","oa_url":"https://aclanthology.org/2022.acl-long.18.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063726130","display_name":"Vaidehi Patil","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":"Vaidehi Patil","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/A5033696194","display_name":"Partha Talukdar","orcid":"https://orcid.org/0000-0001-8825-589X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Partha Talukdar","raw_affiliation_strings":["Google Research, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"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":"Sunita Sarawagi","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":2.0243,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88759637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.8613449335098267},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6403077840805054},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.589882493019104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5773017406463623},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5675513744354248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5309585928916931},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.45544812083244324},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.42174044251441956},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4118993282318115},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11205750703811646},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09024494886398315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613449335098267},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6403077840805054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.589882493019104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5773017406463623},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5675513744354248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5309585928916931},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.45544812083244324},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.42174044251441956},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4118993282318115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11205750703811646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09024494886398315},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.acl-long.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.18","pdf_url":"https://aclanthology.org/2022.acl-long.18.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.acl-long.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.18","pdf_url":"https://aclanthology.org/2022.acl-long.18.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285211844.pdf","grobid_xml":"https://content.openalex.org/works/W4285211844.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W2121879602","https://openalex.org/W2251248591","https://openalex.org/W2278252977","https://openalex.org/W2612309901","https://openalex.org/W2742113707","https://openalex.org/W2891555348","https://openalex.org/W2896457183","https://openalex.org/W2912095972","https://openalex.org/W2953958347","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963979492","https://openalex.org/W2995118574","https://openalex.org/W2995230342","https://openalex.org/W3034469191","https://openalex.org/W3034775979","https://openalex.org/W3035207248","https://openalex.org/W3035390927","https://openalex.org/W3035547806","https://openalex.org/W3035579820","https://openalex.org/W3038047279","https://openalex.org/W3095771422","https://openalex.org/W3099793224","https://openalex.org/W3101498587","https://openalex.org/W3102483398","https://openalex.org/W3105190698","https://openalex.org/W3105421296","https://openalex.org/W3106403484","https://openalex.org/W3136221257","https://openalex.org/W3173172013","https://openalex.org/W3173954987","https://openalex.org/W3197776723","https://openalex.org/W3199276456","https://openalex.org/W4230579319","https://openalex.org/W4287215056","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W4387768015"],"abstract_inverted_index":{"Pre-trained":[0],"multilingual":[1],"language":[2,76,178],"models":[3],"such":[4],"as":[5,191,193],"mBERT":[6],"and":[7,43,125,160],"XLM-R":[8],"have":[9],"demonstrated":[10],"great":[11],"potential":[12],"for":[13],"zero-shot":[14,149,198],"cross-lingual":[15],"transfer":[16,150,199],"to":[17,24,87,106,154,187],"low":[18],"web-resource":[19,40],"languages":[20,41,73],"(LRL).":[21],"However,":[22],"due":[23],"limited":[25],"model":[26],"capacity,":[27],"the":[28,32,52,55,59,79,91,107,136,167,175,185],"large":[29],"difference":[30],"in":[31,74,147,174,197],"sizes":[33],"of":[34,50,63,81,90,94,138,169],"available":[35],"monolingual":[36],"corpora":[37,92],"between":[38],"high":[39],"(HRL)":[42],"LRLs":[44,139,155],"does":[45],"not":[46],"provide":[47],"enough":[48],"scope":[49],"co-embedding":[51],"LRL":[53],"with":[54,143],"HRL,":[56],"thereby":[57],"affecting":[58],"downstream":[60],"task":[61],"performance":[62],"LRLs.":[64,95],"In":[65],"this":[66],"paper,":[67],"we":[68,127,171],"argue":[69],"that":[70,129,134,165,173],"relatedness":[71],"among":[72],"a":[75,101,132,194],"family":[77],"along":[78],"dimension":[80],"lexical":[82],"overlap":[83,114,181,186],"may":[84],"be":[85],"leveraged":[86],"overcome":[88],"some":[89],"limitations":[93],"We":[96],"propose":[97],"Overlap":[98],"BPE":[99,108],"(OBPE),":[100],"simple":[102],"yet":[103],"effective":[104],"modification":[105],"vocabulary":[109,133],"generation":[110],"algorithm":[111],"which":[112],"enhances":[113],"across":[115],"related":[116,152,177],"languages.":[117],"Through":[118],"extensive":[119],"experiments":[120],"on":[121],"multiple":[122],"NLP":[123],"tasks":[124],"datasets,":[126],"observe":[128],"OBPE":[130],"generates":[131],"increases":[135],"representation":[137,159],"via":[140],"tokens":[141],"shared":[142],"HRLs.":[144],"This":[145],"results":[146],"improved":[148],"from":[151],"HRLs":[153],"without":[156],"reducing":[157,184],"HRL":[158],"accuracy.":[161,200],"Unlike":[162],"previous":[163],"studies":[164],"dismissed":[166],"importance":[168],"token-overlap,":[170],"show":[172],"low-resource":[176],"setting,":[179],"token":[180],"matters.":[182],"Synthetically":[183],"zero":[188],"can":[189],"cause":[190],"much":[192],"four-fold":[195],"drop":[196]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}