{"id":"https://openalex.org/W7166847004","doi":"https://doi.org/10.18653/v1/2026.acl-long.352","title":"DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation","display_name":"DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166847004","doi":"https://doi.org/10.18653/v1/2026.acl-long.352"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.352","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.352","pdf_url":"https://aclanthology.org/2026.acl-long.352.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.352.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139773880","display_name":"Boyu Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Guan","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735993","display_name":"Chuang Han","orcid":"https://orcid.org/0009-0006-0753-3506"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Han","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745857","display_name":"Yang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139716752","display_name":"Chengqing Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.84657582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7752","last_page":"7772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3765000104904175,"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":0.3765000104904175,"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":0.2831999957561493,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0333000011742115,"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/machine-translation","display_name":"Machine translation","score":0.46790000796318054},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3522000014781952},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26350000500679016},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.23469999432563782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555999875068665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.38519999384880066},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23469999432563782},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2345000058412552},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2290000021457672}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.352","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.352","pdf_url":"https://aclanthology.org/2026.acl-long.352.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.352","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.352","pdf_url":"https://aclanthology.org/2026.acl-long.352.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1883487206","display_name":null,"funder_award_id":"62336008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2799814136","display_name":null,"funder_award_id":"62476271","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166847004.pdf","grobid_xml":"https://content.openalex.org/works/W7166847004.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video-guided":[0],"Machine":[1,49],"Translation":[2],"(VMT)":[3],"seeks":[4],"to":[5,35,54,98,144,173],"enhance":[6],"translation":[7,133],"quality":[8,134],"by":[9,112],"incorporating":[10],"contextual":[11],"information":[12,27,105,125],"derived":[13],"from":[14],"paired":[15],"short":[16],"video":[17,104],"clips.However,":[18],"many":[19],"VMT":[20],"samples":[21,102],"are":[22,33],"text-sufficient;":[23],"even":[24],"when":[25],"visual":[26,78],"is":[28,52,106,153],"needed,":[29],"only":[30],"minimal":[31],"cues":[32],"required.Aiming":[34],"tackle":[36],"these":[37],"issues,":[38],"we":[39,80],"propose":[40],"a":[41,87],"novel":[42],"framework":[43],"DART":[44],"(Disambiguation-Aware":[45],"Reasoning":[46],"for":[47,90],"Videoguided":[48],"Translation).Reinforcement":[50],"learning":[51],"used":[53],"incorporate":[55],"multimodal":[56,60,71,96,124],"large":[57],"language":[58],"models'":[59],"reasoning":[61],"into":[62],"VMT.The":[63],"model":[64],"dynamically":[65],"switches":[66],"between":[67],"text-only":[68],"processing":[69],"and":[70,135],"integration,":[72],"contingent":[73],"on":[74,95],"the":[75,146,151,175],"necessity":[76],"of":[77],"disambiguation.Furthermore,":[79],"present":[81],"TVRF":[82],"(Translation-oriented":[83],"Video":[84],"Relevance":[85],"Filtering),":[86],"systematic":[88],"pipeline":[89,100],"constructing":[91],"training":[92,109],"data":[93,114],"based":[94],"relevance":[97],"translation.This":[99],"filters":[101],"where":[103],"translationrelevant,":[107],"mitigating":[108],"collapse":[110],"caused":[111],"video-irrelevant":[113],"in":[115,127,131,156],"conventional":[116],"VMT.Experimental":[117],"results":[118],"show":[119],"that":[120],"our":[121],"approach":[122],"improves":[123],"utilization":[126],"VMT,":[128],"yielding":[129],"gains":[130],"both":[132],"computational":[136],"efficiency.*":[137],"Equal":[138],"corresponding":[139],"authors.Reasoning:":[140],"Okay,":[141,169],"I":[142,171],"need":[143,172],"translate":[145,174],"input":[147],"sentence":[148,176],"...":[149],"So":[150],"answer":[152],"\"\u54e6\uff01\".(809":[154],"tokens":[155],"total)":[157],"DA":[158],"T":[159],"Existing":[160],"LMRMs":[161],"\u2026":[162],"\"It's":[163],"hitting":[164],"his":[165],"yacht.\"Translation:":[166],"\u54e6\uff01(Oh!)":[167],"Reasoning:":[168],"so":[170],"..":[177]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}
