{"id":"https://openalex.org/W4387968215","doi":"https://doi.org/10.1145/3581783.3611992","title":"Cross-Lingual Transfer of Large Language Model by Visually-Derived Supervision Toward Low-Resource Languages","display_name":"Cross-Lingual Transfer of Large Language Model by Visually-Derived Supervision Toward Low-Resource Languages","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968215","doi":"https://doi.org/10.1145/3581783.3611992"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611992","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611992","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004152333","display_name":"Masayasu Muraoka","orcid":"https://orcid.org/0009-0004-3620-1231"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masayasu Muraoka","raw_affiliation_strings":["IBM Research, Chuo-ku, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research, Chuo-ku, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069125151","display_name":"Bishwaranjan Bhattacharjee","orcid":"https://orcid.org/0009-0009-7097-4891"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bishwaranjan Bhattacharjee","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068061267","display_name":"Michele Merler","orcid":"https://orcid.org/0000-0002-4358-8671"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michele Merler","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076476382","display_name":"Graeme Blackwood","orcid":"https://orcid.org/0009-0004-0609-7613"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graeme Blackwood","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035840897","display_name":"Yulong Li","orcid":"https://orcid.org/0000-0003-3412-0732"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulong Li","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101528325","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-3774-6773"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["IBM Research, Chuo-ku, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research, Chuo-ku, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004152333"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65990695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3637","last_page":"3646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9939000010490417,"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":0.7854024767875671},{"id":"https://openalex.org/keywords/swahili","display_name":"Swahili","score":0.6106802225112915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6100454330444336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5783870220184326},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5254548788070679},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.5179280638694763},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.49432992935180664},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.4343724846839905},{"id":"https://openalex.org/keywords/constructed-language","display_name":"Constructed language","score":0.41871803998947144},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28192099928855896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854024767875671},{"id":"https://openalex.org/C2779913364","wikidata":"https://www.wikidata.org/wiki/Q7838","display_name":"Swahili","level":2,"score":0.6106802225112915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6100454330444336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5783870220184326},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5254548788070679},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.5179280638694763},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.49432992935180664},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.4343724846839905},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.41871803998947144},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28192099928855896},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611992","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611992","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968215.pdf","grobid_xml":"https://content.openalex.org/works/W4387968215.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W288653040","https://openalex.org/W1732736211","https://openalex.org/W1861492603","https://openalex.org/W1863849972","https://openalex.org/W2022214202","https://openalex.org/W2048343491","https://openalex.org/W2077947298","https://openalex.org/W2096733369","https://openalex.org/W2138621090","https://openalex.org/W2150593711","https://openalex.org/W2250976127","https://openalex.org/W2252200119","https://openalex.org/W2277195237","https://openalex.org/W2568389463","https://openalex.org/W2889326414","https://openalex.org/W2891555348","https://openalex.org/W2949579048","https://openalex.org/W2963264012","https://openalex.org/W2963909453","https://openalex.org/W2979826702","https://openalex.org/W2998702515","https://openalex.org/W3035463087","https://openalex.org/W3035579820","https://openalex.org/W3045462440","https://openalex.org/W3106150792","https://openalex.org/W3156394741","https://openalex.org/W3172424021","https://openalex.org/W3174010726","https://openalex.org/W3177777394","https://openalex.org/W3212867526","https://openalex.org/W4205480697","https://openalex.org/W4312245858","https://openalex.org/W4312528757","https://openalex.org/W4385572711","https://openalex.org/W6610365113"],"related_works":["https://openalex.org/W2024870452","https://openalex.org/W4232455167","https://openalex.org/W2589694904","https://openalex.org/W2023610355","https://openalex.org/W1964726137","https://openalex.org/W2504430991","https://openalex.org/W2563737361","https://openalex.org/W2389435148","https://openalex.org/W1878765434","https://openalex.org/W2596449829"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"on":[2,118],"vision":[3],"and":[4,113,123,159,168],"language":[5,17,23,96],"research":[6],"has":[7],"shown":[8],"that":[9,85,138,171],"visual":[10,39,48,63,86],"supervision":[11,49,87],"improves":[12,146],"the":[13,29,45,60,127,147,172,179],"performance":[14,149],"of":[15,37,47,62,174],"large":[16],"models":[18],"(LLMs)":[19],"in":[20,53,65,79,100,125,150],"various":[21],"natural":[22],"processing":[24],"(NLP)":[25],"tasks.":[26],"In":[27],"particular,":[28],"Vokenization":[30,111],"approach":[31,176],"[65]":[32],"initiated":[33],"a":[34,54,94,109,115],"new":[35],"way":[36],"incorporating":[38],"information":[40,64],"into":[41],"LLM":[42,117,148],"training,":[43],"demonstrating":[44],"potential":[46],"for":[50,162],"NLP":[51,101,153],"tasks":[52,154,161],"monolingual":[55],"(i.e.,":[56],"English)":[57],"setting.":[58],"Given":[59],"effectiveness":[61],"human":[66],"communication":[67],"among":[68],"people":[69],"who":[70],"speak":[71],"different":[72],"languages,":[73,120],"we":[74,83,107],"tackle":[75],"an":[76],"ambitious":[77],"question":[78],"this":[80,105],"paper;":[81],"can":[82],"expect":[84],"contributes":[88],"to":[89,97],"cross-lingual":[90,110,116,141,152],"transfer":[91,142],"learning":[92,143],"from":[93],"high-resource":[95,184],"low-resource":[98,132,163],"languages":[99,185],"tasks?":[102],"To":[103],"study":[104],"hypothesis,":[106],"build":[108],"model":[112],"train":[114],"three":[119],"English,":[121],"Urdu,":[122],"Swahili,":[124],"which":[126],"last":[128],"two":[129],"are":[130],"considered":[131],"languages.":[133,164],"The":[134],"experimental":[135],"results":[136],"demonstrate":[137,170],"our":[139,175],"visually-supervised":[140],"method":[144],"significantly":[145],"multiple":[151],"such":[155],"as":[156,178],"XNLI,":[157],"NER,":[158],"TyDiQA":[160],"We":[165],"also":[166],"qualitatively":[167],"quantitatively":[169],"benefit":[173],"increases":[177],"linguistic":[180],"distance":[181],"between":[182],"low-and":[183],"grows":[186],"larger.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}