{"id":"https://openalex.org/W4412889452","doi":"https://doi.org/10.18653/v1/2025.acl-srw.6","title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","display_name":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889452","doi":"https://doi.org/10.18653/v1/2025.acl-srw.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-srw.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.6","pdf_url":"https://aclanthology.org/2025.acl-srw.6.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-srw.6.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181765","display_name":"Enes \u00d6zeren","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Enes \u00d6zeren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101584624","display_name":"Yihong Liu","orcid":"https://orcid.org/0000-0003-1073-0958"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihong Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088559117","display_name":"Hinrich Schuetze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hinrich Schuetze","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119181765"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10016531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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":0.9954000115394592,"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":0.7752889394760132},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7207716703414917},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7207306623458862},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5965033769607544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37858182191848755},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3477821946144104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3402584493160248},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3273020386695862},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19015809893608093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752889394760132},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7207716703414917},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7207306623458862},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5965033769607544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37858182191848755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3477821946144104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3402584493160248},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3273020386695862},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19015809893608093},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-srw.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.6","pdf_url":"https://aclanthology.org/2025.acl-srw.6.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-srw.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.6","pdf_url":"https://aclanthology.org/2025.acl-srw.6.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324306","display_name":"Bayerische Akademie der Wissenschaften","ror":"https://ror.org/001rdaz60"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320336863","display_name":"Leibniz-Rechenzentrum","ror":"https://ror.org/05558nw16"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889452.pdf","grobid_xml":"https://content.openalex.org/works/W4412889452.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2932872266"],"abstract_inverted_index":{"Many":[0],"pre-trained":[1],"language":[2],"models":[3],"(PLMs)":[4],"exhibit":[5],"suboptimal":[6],"performance":[7,156],"on":[8,44],"mid-and":[9],"lowresource":[10],"languages,":[11,36],"largely":[12],"due":[13],"to":[14,17,24,28,33,72,105,114],"limited":[15],"exposure":[16],"these":[18],"languages":[19],"during":[20],"pre-training.A":[21],"common":[22],"strategy":[23],"address":[25],"this":[26,88],"is":[27,62,103],"introduce":[29],"new":[30],"tokens":[31],"specific":[32],"the":[34,115,155,169],"target":[35],"initialize":[37],"their":[38],"embeddings,":[39,82],"and":[40,65,151,164],"apply":[41],"continual":[42,141,161],"pre-training":[43,162],"target-language":[45,69,132],"data.Among":[46],"such":[47],"methods,":[48],"OFA":[49,67,158],"(Liu":[50],"et":[51],"al.,":[52],"2024a)":[53],"proposes":[54],"a":[55,77,93,136],"similarity-based":[56],"subword":[57],"embedding":[58,100,118],"initialization":[59,149],"heuristic":[60],"that":[61,144],"both":[63,160],"effective":[64],"efficient.However,":[66],"restricts":[68],"token":[70,99,117],"embeddings":[71,130],"be":[73],"convex":[74],"combinations":[75],"of":[76,80,157],"fixed":[78],"number":[79],"source-language":[81,121],"which":[83],"may":[84],"limit":[85],"expressiveness.To":[86],"overcome":[87],"limitation,":[89],"we":[90],"propose":[91],"HYPEROFA,":[92],"hypernetwork-based":[94],"approach":[95],"for":[96,131,140],"more":[97],"adaptive":[98],"initialization.The":[101],"hypernetwork":[102],"trained":[104],"map":[106],"from":[107],"an":[108],"external":[109],"multilingual":[110],"word":[111],"vector":[112],"space":[113,119],"PLM's":[116],"using":[120],"tokens.":[122],"1":[123],"Once":[124],"trained,":[125],"it":[126],"can":[127],"generate":[128],"flexible":[129],"tokens,":[133],"serving":[134],"as":[135],"good":[137],"starting":[138],"point":[139],"pretraining.Experiments":[142],"demonstrate":[143],"HYPEROFA":[145],"consistently":[146],"outperforms":[147],"random":[148],"baseline":[150],"matches":[152],"or":[153],"exceeds":[154],"in":[159],"convergence":[163],"downstream":[165],"task":[166],"performance.We":[167],"make":[168],"code":[170],"publicly":[171],"available.":[172],"2":[173]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}