{"id":"https://openalex.org/W4404780767","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","title":"Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models","display_name":"Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404780767","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.863"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.863","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","pdf_url":"https://aclanthology.org/2024.findings-emnlp.863.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-emnlp.863.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009214191","display_name":"Gunjan Balde","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gunjan Balde","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010730449","display_name":"Soumyadeep Roy","orcid":"https://orcid.org/0000-0001-7269-2163","observed_orcids":["https://orcid.org/0000-0001-7269-2163"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumyadeep Roy","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002813297","display_name":"Mainack Mondal","orcid":"https://orcid.org/0000-0003-4317-0184","observed_orcids":["https://orcid.org/0000-0003-4317-0184"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mainack Mondal","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073812421","display_name":"Niloy Ganguly","orcid":"https://orcid.org/0000-0002-3967-186X","observed_orcids":["https://orcid.org/0000-0002-3967-186X"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niloy Ganguly","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":1.2215,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.828204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14724","last_page":"14733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8939999938011169,"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":0.8939999938011169,"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":0.06319999694824219,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03240000084042549,"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/byte-pair-encoding","display_name":"byte pair encoding","score":0.8090000152587891},{"id":"https://openalex.org/keywords/vocabulary-adaptation","display_name":"vocabulary adaptation","score":0.9290000200271606},{"id":"https://openalex.org/keywords/domain-specific-vocabulary","display_name":"domain-specific terminology","score":0.6480000019073486},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.6579999923706055},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.781000018119812},{"id":"https://openalex.org/keywords/medical-text-summarization","display_name":"medical text summarization","score":0.718999981880188},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050684332847595},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7000816464424133},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6284826397895813},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.558702290058136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336312711238861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3974463641643524},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09538331627845764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06557992100715637},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06370100378990173},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.863","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","pdf_url":"https://aclanthology.org/2024.findings-emnlp.863.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.03258","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.03258","pdf_url":"https://arxiv.org/pdf/2410.03258","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.03258","doi":"https://doi.org/10.48550/arxiv.2410.03258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.03258","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.863","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.863","pdf_url":"https://aclanthology.org/2024.findings-emnlp.863.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404780767.pdf","grobid_xml":"https://content.openalex.org/works/W4404780767.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2525778437","https://openalex.org/W2965373594","https://openalex.org/W4283021420","https://openalex.org/W4322718191","https://openalex.org/W4384918448","https://openalex.org/W4387561528","https://openalex.org/W4404783106"],"related_works":["https://openalex.org/W7140126971","https://openalex.org/W7140131454","https://openalex.org/W7166808098","https://openalex.org/W7172378170","https://openalex.org/W4396814525","https://openalex.org/W4416035830","https://openalex.org/W4404781979","https://openalex.org/W3199359833","https://openalex.org/W4415143708","https://openalex.org/W7172407664"],"abstract_inverted_index":{"In":[0],"this":[1,69],"work,":[2],"we":[3,71],"show":[4],"a":[5,48,65,150],"fundamental":[6],"limitation":[7],"in":[8,56,146],"vocabulary":[9,34,93],"adaptation":[10],"approaches":[11,28],"that":[12,58,154],"use":[13],"Byte-Pair":[14],"Encoding":[15],"(BPE)":[16],"tokenization":[17,55,77],"scheme":[18],"for":[19,131],"fine-tuning":[20],"pretrained":[21],"language":[22],"models":[23],"(PLMs)":[24],"to":[25,47,63,82,165],"expert":[26],"domains.Current":[27],"trivially":[29],"append":[30],"the":[31,39,42,75,85,90,97,107],"target":[32],"domainspecific":[33],"(V":[35],"DOMAIN":[36],")":[37],"at":[38,96,172],"end":[40],"of":[41,104,122,128],"PLM":[43],"vocabulary.This":[44],"approach":[45],"leads":[46],"lower":[49],"priority":[50],"score":[51],"and":[52,113,124,159],"causes":[53],"sub-optimal":[54],"BPE":[57,76,109],"iteratively":[59],"uses":[60],"merge":[61],"rules":[62],"tokenize":[64],"given":[66],"text.To":[67],"mitigate":[68],"issue,":[70],"propose":[72],"ADAPTBPE":[73,105,116,155],"where":[74],"initialization":[78],"phase":[79],"is":[80],"modified":[81],"first":[83],"perform":[84,100],"longest":[86],"string":[87],"matching":[88],"on":[89],"added":[91],"(target)":[92],"before":[94],"tokenizing":[95],"character":[98],"level.We":[99],"an":[101],"extensive":[102],"evaluation":[103],"versus":[106],"standard":[108],"over":[110],"various":[111],"classification":[112],"summarization":[114],"tasks;":[115],"improves":[117],"by":[118],"3.57%":[119],"(in":[120,126],"terms":[121,127],"accuracy)":[123],"1.87%":[125],"Rouge-L),":[129],"respectively.ADAPTBPE":[130],"MED-VOC":[132],"works":[133],"particularly":[134],"well":[135],"when":[136],"reference":[137],"summaries":[138,162],"have":[139],"high":[140],"OOV":[141],"concentration":[142],"or":[143],"are":[144],"longer":[145],"length.We":[147],"also":[148],"conduct":[149],"human":[151],"evaluation,":[152],"revealing":[153],"generates":[156],"more":[157,160],"relevant":[158],"faithful":[161],"as":[163],"compared":[164],"MEDVOC.We":[166],"make":[167],"our":[168],"codebase":[169],"publicly":[170],"available":[171],"https://github.com/":[173],"gb-kgp/adaptbpe.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-28T00:00:00"}