{"id":"https://openalex.org/W4416035204","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.163","title":"NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining","display_name":"NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035204","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.163"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.163","pdf_url":"https://aclanthology.org/2025.findings-emnlp.163.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.163.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100769231","display_name":"Sicheng Wang","orcid":"https://orcid.org/0000-0002-5224-5697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sicheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100887740","display_name":"Wenyi Wu","orcid":"https://orcid.org/0000-0001-9344-3406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115596278","display_name":"Zibo Zhang","orcid":"https://orcid.org/0009-0000-3685-9069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zibo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.15784877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3019","last_page":"3030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.815500020980835,"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":0.815500020980835,"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/T10028","display_name":"Topic Modeling","score":0.03200000151991844,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.029400000348687172,"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/transfer","display_name":"Transfer (computing)","score":0.34850001335144043},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3084999918937683},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.3034999966621399},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27469998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.539900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45669999718666077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28870001435279846},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.163","pdf_url":"https://aclanthology.org/2025.findings-emnlp.163.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.163","pdf_url":"https://aclanthology.org/2025.findings-emnlp.163.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035204.pdf","grobid_xml":"https://content.openalex.org/works/W4416035204.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,49,112],"multilingual":[3,103],"pretraining":[4,60,87],"has":[5],"yielded":[6],"strong":[7],"performance":[8],"on":[9,74,105],"high-resource":[10],"languages,":[11],"albeit":[12],"with":[13],"limited":[14,40],"generalization":[15],"to":[16,24,45,88],"genuinely":[17],"low-resource":[18],"settings.While":[19],"prior":[20],"approaches":[21],"have":[22],"attempted":[23],"enhance":[25],"crosslingual":[26],"transfer":[27,118],"through":[28],"representation":[29],"alignment":[30],"or":[31,77],"contrastive":[32,59],"learning,":[33],"they":[34],"remain":[35],"constrained":[36],"by":[37,66],"the":[38,108],"extremely":[39],"availability":[41],"of":[42,110],"parallel":[43],"data":[44],"provide":[46],"positive":[47,91],"supervision":[48,65],"target":[50],"languages.In":[51],"this":[52],"work,":[53],"we":[54],"introduce":[55],"NeighXLM,":[56],"a":[57],"neighbor-augmented":[58],"framework":[61],"that":[62],"enriches":[63],"target-language":[64],"mining":[67],"semantic":[68,83],"neighbors":[69],"from":[70],"unlabeled":[71],"corpora.Without":[72],"relying":[73],"human":[75],"annotations":[76],"translation":[78],"systems,":[79],"NeighXLM":[80,111],"exploits":[81],"intra-language":[82],"relationships":[84],"captured":[85],"during":[86],"construct":[89],"high-quality":[90],"pairs.The":[92],"approach":[93],"is":[94],"model-agnostic":[95],"and":[96,116],"can":[97],"be":[98],"seamlessly":[99],"integrated":[100],"into":[101],"existing":[102],"pipelines.Experiments":[104],"Swahili":[106],"demonstrate":[107],"effectiveness":[109],"improving":[113],"cross-lingual":[114],"retrieval":[115],"zero-shot":[117],"performance.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}