{"id":"https://openalex.org/W7166798953","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1556","title":"Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts","display_name":"Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166798953","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1556"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1556","pdf_url":"https://aclanthology.org/2026.findings-acl.1556.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1556.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069648486","display_name":"\uae40\uc7ac\ud76c","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehee Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103378802","display_name":"Ji Hoon Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Hoon Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730953","display_name":"Seoyoon Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seoyoon Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139787215","display_name":"Unsol Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Unsol Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139739702","display_name":"Kyungwon Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyungwon Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797234","display_name":"JiHak Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JiHak Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139800999","display_name":"Yi-Jun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Jun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139781701","display_name":"Hansaem Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansaem Kim","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":0.94174757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31109","last_page":"31124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.11169999837875366,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.11169999837875366,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.07729999721050262,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.37790000438690186},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.33250001072883606},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.30140000581741333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2840000092983246},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2619999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4763000011444092},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4284000098705292},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1556","pdf_url":"https://aclanthology.org/2026.findings-acl.1556.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1556","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1556","pdf_url":"https://aclanthology.org/2026.findings-acl.1556.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.47347211837768555}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321314","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166798953.pdf","grobid_xml":"https://content.openalex.org/works/W7166798953.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Indirect":[0],"speech":[1],"acts":[2],"(ISAs)":[3],"require":[4],"pragmatic":[5,60,72,113,125],"reasoning":[6,53,126],"over":[7,54],"context,":[8],"since":[9],"directive":[10],"intent":[11],"cannot":[12],"be":[13],"inferred":[14],"from":[15],"surface":[16],"form":[17],"alone.Prior":[18],"text-based":[19],"studies":[20],"and":[21,57,66,81],"multimodal":[22,45,87,116],"benchmarks":[23],"largely":[24],"overlook":[25],"this,":[26],"focusing":[27],"on":[28],"explicitly":[29],"encoded":[30],"context":[31,56],"or":[32],"perceptual":[33],"recognition":[34],"particularly":[35],"in":[36,59,79,103,115],"high-context":[37],"languages":[38],"such":[39],"as":[40,70,97],"Korean.We":[41],"introduce":[42],"READI,":[43],"a":[44],"benchmark":[46],"that":[47,84],"evaluates":[48],"ISA":[49],"understanding":[50,114],"through":[51],"integrated":[52],"visual":[55,71],"dialogue.Grounded":[58],"theory,":[61],"READI":[62],"models":[63,88],"graded":[64],"indirectness":[65,98],"formulates":[67],"the":[68,124],"task":[69],"question":[73],"answering":[74],"(V-PQA),":[75],"enabling":[76],"crosslingual":[77],"evaluation":[78,108],"English":[80],"Korean.Experiments":[82],"show":[83],"even":[85],"state-of-the-art":[86],"struggle":[89],"with":[90,94],"visually":[91],"grounded":[92],"ISAs":[93],"performance":[95],"declining":[96],"increases,":[99],"revealing":[100],"fundamental":[101],"limitations":[102],"interpreting":[104],"indirectness.By":[105],"proposing":[106],"an":[107],"paradigm":[109],"for":[110,122],"systematically":[111],"assessing":[112],"settings,":[117],"this":[118],"study":[119],"provides":[120],"directions":[121],"improving":[123],"abilities":[127],"of":[128],"language":[129],"models.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
