{"id":"https://openalex.org/W4416034892","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.536","title":"VQA-Augmented Machine Translation with Cross-Modal Contrastive Learning","display_name":"VQA-Augmented Machine Translation with Cross-Modal Contrastive Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034892","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.536"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.536","pdf_url":"https://aclanthology.org/2025.findings-emnlp.536.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.536.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086006864","display_name":"Zhihui Zhang","orcid":"https://orcid.org/0000-0002-0277-4937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihui Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613714","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0001-5627-4156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022765433","display_name":"Tengfei Song","orcid":"https://orcid.org/0000-0002-2610-4049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tengfei Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748251","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0003-3590-4491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.30035497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10113","last_page":"10124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8101999759674072,"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":0.8101999759674072,"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":0.04919999837875366,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.014000000432133675,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5821999907493591},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.3206999897956848},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6035000085830688},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5821999907493591},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3492000102996826},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.536","pdf_url":"https://aclanthology.org/2025.findings-emnlp.536.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.536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.536","pdf_url":"https://aclanthology.org/2025.findings-emnlp.536.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":[{"id":"https://openalex.org/G6487037979","display_name":null,"funder_award_id":"62476089","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322370","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034892.pdf","grobid_xml":"https://content.openalex.org/works/W4416034892.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"machine":[1],"translation":[2,7],"(MMT)":[3],"aims":[4],"to":[5,29,36,87],"enhance":[6,88],"quality":[8],"by":[9,39],"integrating":[10],"visual":[11,17,41,95],"information.However,":[12],"existing":[13],"methods":[14,32,123],"often":[15],"extract":[16],"features":[18,25],"using":[19],"pretrained":[20],"models":[21],"while":[22,97],"learning":[23],"text":[24,62,66],"from":[26],"scratch,":[27],"leading":[28],"representation":[30],"imbalance.These":[31],"are":[33],"also":[34,98],"prone":[35],"being":[37],"misled":[38],"redundant":[40],"information,":[42],"which":[43,118],"results":[44],"in":[45],"suboptimal":[46],"performance.To":[47],"address":[48],"these":[49],"challenges,":[50],"we":[51,78],"propose":[52],"CAMT,":[53],"a":[54],"novel":[55],"cross-modal":[56],"VQA-augmented":[57],"MMT":[58,122],"method.CAMT":[59],"aligns":[60],"image-source":[61],"pairs":[63,67,86],"and":[64,91],"image-question":[65],"through":[68],"dual-text":[69],"contrastive":[70],"learning,":[71],"thereby":[72],"improving":[73],"semantic":[74],"consistency":[75],"across":[76,124],"modalities.Additionally,":[77],"design":[79],"an":[80],"effective":[81],"strategy":[82],"for":[83],"generating":[84],"question-answer":[85],"fine-grained":[89],"alignment":[90],"filter":[92],"out":[93],"irrelevant":[94],"noise,":[96],"addressing":[99],"the":[100,111,114],"scarcity":[101],"of":[102,113],"VQA":[103],"annotations.Extensive":[104],"experiments":[105],"on":[106],"multiple":[107,125],"benchmark":[108],"datasets":[109],"demonstrate":[110],"effectiveness":[112],"proposed":[115],"CAMT":[116],"framework,":[117],"consistently":[119],"outperforms":[120],"state-of-the-art":[121],"evaluation":[126],"metrics.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}