{"id":"https://openalex.org/W4412889472","doi":"https://doi.org/10.18653/v1/2025.acl-short.95","title":"Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning","display_name":"Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889472","doi":"https://doi.org/10.18653/v1/2025.acl-short.95"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-short.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.95","pdf_url":"https://aclanthology.org/2025.acl-short.95.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 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-short.95.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050340761","display_name":"Nathaniel Krasner","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Krasner","raw_affiliation_strings":["Department of Computer Science , George Mason University ; Fairfax , VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University ; Fairfax , VA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181775","display_name":"Nicholas Lanuzo","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Lanuzo","raw_affiliation_strings":["Department of Computer Science , George Mason University ; Fairfax , VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University ; Fairfax , VA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Department of Computer Science , George Mason University ; Fairfax , VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University ; Fairfax , VA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1193","last_page":"1199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9907000064849854,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9800999760627747,"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":0.7570822834968567},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6616203784942627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272136569023132},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5105563402175903},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49199578166007996},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48205289244651794},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3481348752975464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570822834968567},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6616203784942627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272136569023132},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5105563402175903},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49199578166007996},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48205289244651794},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3481348752975464},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-short.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.95","pdf_url":"https://aclanthology.org/2025.acl-short.95.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 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-short.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.95","pdf_url":"https://aclanthology.org/2025.acl-short.95.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 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7185756783","display_name":"EAGER: Building Language Technologies by Machine Reading Grammars","funder_award_id":"2327143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G841383084","display_name":null,"funder_award_id":"IIS-2327143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309029","display_name":"George Mason University","ror":"https://ror.org/02jqj7156"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889472.pdf","grobid_xml":"https://content.openalex.org/works/W4412889472.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W2352227742","https://openalex.org/W4390679071","https://openalex.org/W1967645776","https://openalex.org/W3006966347"],"abstract_inverted_index":{"Multilingual":[0],"alignment":[1,49,70],"of":[2],"sentence":[3],"representations":[4,55,75],"has":[5],"mostly":[6],"required":[7],"bitexts":[8],"to":[9,29],"bridge":[10,20],"the":[11,53,61],"gap":[12,22],"between":[13,56],"languages.We":[14,44],"investigate":[15],"whether":[16],"visual":[17],"information":[18],"can":[19,50,65],"this":[21,36,69],"instead.Image":[23],"caption":[24],"datasets":[25],"are":[26,76],"very":[27],"easy":[28],"create":[30],"without":[31],"requiring":[32],"multilingual":[33,47],"expertise,":[34],"so":[35],"offers":[37],"a":[38],"more":[39],"efficient":[40],"alternative":[41],"for":[42,78],"low-resource":[43],"find":[45],"that":[46],"image-caption":[48],"implicitly":[51],"align":[52],"text":[54],"languages,":[57],"languages":[58],"unseen":[59],"by":[60],"encoder":[62],"in":[63],"pretraining":[64],"be":[66],"incorporated":[67],"into":[68],"post-hoc,":[71],"and":[72,84],"these":[73],"aligned":[74],"usable":[77],"cross-lingual":[79],"Natural":[80],"Language":[81],"Understanding":[82],"(NLU)":[83],"bitext":[85],"retrieval.":[86],"1":[87]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}