{"id":"https://openalex.org/W4412944967","doi":"https://doi.org/10.18653/v1/2025.acl-long.893","title":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","display_name":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944967","doi":"https://doi.org/10.18653/v1/2025.acl-long.893"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.893","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.893","pdf_url":"https://aclanthology.org/2025.acl-long.893.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 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.893.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111482115","display_name":"Zeli Su","orcid":"https://orcid.org/0009-0007-5271-8451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeli Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022625306","display_name":"Ziyin Zhang","orcid":"https://orcid.org/0000-0001-6530-6738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042529505","display_name":"Guixian Xu","orcid":"https://orcid.org/0000-0001-8815-479X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guixian Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785476","display_name":"Jianing Liu","orcid":"https://orcid.org/0000-0002-2539-7142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226207","display_name":"Xu Han","orcid":"https://orcid.org/0000-0003-0028-3218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458375","display_name":"Ting Zhang","orcid":"https://orcid.org/0000-0003-4445-3813"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101985055","display_name":"Yi Dong","orcid":"https://orcid.org/0000-0002-4400-6901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushuang Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.17427555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18259","last_page":"18270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9483000040054321,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9483000040054321,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7339960932731628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7070221900939941},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6002466678619385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3951437473297119},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3393763601779938},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17137488722801208},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10739222168922424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339960932731628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7070221900939941},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6002466678619385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3951437473297119},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3393763601779938},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17137488722801208},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10739222168922424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.893","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.893","pdf_url":"https://aclanthology.org/2025.acl-long.893.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 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.893","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.893","pdf_url":"https://aclanthology.org/2025.acl-long.893.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 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944967.pdf","grobid_xml":"https://content.openalex.org/works/W4412944967.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"While":[0],"multilingual":[1,60],"language":[2],"models":[3,42],"like":[4],"XLM-R":[5],"have":[6],"advanced":[7],"multilingualism":[8],"in":[9,15,47,65,98],"NLP,":[10],"they":[11],"still":[12],"perform":[13],"poorly":[14],"extremely":[16,66],"low-resource":[17,67,99],"languages.This":[18],"situation":[19],"is":[20],"exacerbated":[21],"by":[22],"the":[23,48,70,73,76,81,85,90],"fact":[24],"that":[25],"modern":[26],"LLMs":[27],"such":[28],"as":[29],"LLaMA":[30],"and":[31,75,95,111],"Qwen":[32],"support":[33],"far":[34],"fewer":[35],"languages":[36,46],"than":[37],"XLM-R,":[38],"making":[39],"text":[40,63],"generation":[41,64],"non-existent":[43],"for":[44,58],"many":[45],"world.To":[49],"tackle":[50],"this":[51,101],"challenge,":[52],"we":[53,108],"propose":[54],"a":[55],"novel":[56],"framework":[57,79,102],"adapting":[59],"encoders":[61],"to":[62,83,103],"languages.By":[68],"reusing":[69],"weights":[71],"between":[72],"encoder":[74],"decoder,":[77],"our":[78],"allows":[80],"model":[82],"leverage":[84],"learned":[86],"semantic":[87],"space":[88],"of":[89],"encoder,":[91],"enabling":[92],"efficient":[93],"learning":[94],"effective":[96],"generalization":[97],"languages.Applying":[100],"four":[104],"Chinese":[105],"minority":[106],"languages,":[107],"present":[109],"XLM-SWCM,":[110],"demonstrate":[112],"its":[113],"superior":[114],"performance":[115],"on":[116],"various":[117],"downstream":[118],"tasks":[119],"even":[120],"when":[121],"compared":[122],"with":[123],"much":[124],"larger":[125],"models.":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
