{"id":"https://openalex.org/W4412945389","doi":"https://doi.org/10.18653/v1/2025.acl-long.547","title":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","display_name":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945389","doi":"https://doi.org/10.18653/v1/2025.acl-long.547"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.547","pdf_url":"https://aclanthology.org/2025.acl-long.547.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 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/2025.acl-long.547.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094264753","display_name":"Shun Inadumi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shun Inadumi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047419744","display_name":"Nobuhiro Ueda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuhiro Ueda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11183","last_page":"11198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9940000176429749,"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/T12031","display_name":"Speech and dialogue systems","score":0.9940000176429749,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9681000113487244,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9024999737739563,"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":0.7673377990722656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6731066703796387},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6205681562423706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503422200679779},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.46428051590919495},{"id":"https://openalex.org/keywords/joint-attention","display_name":"Joint attention","score":0.42702195048332214},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37284722924232483},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35412895679473877},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35046327114105225},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14471808075904846},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.08676835894584656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07700255513191223},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06356564164161682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673377990722656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6731066703796387},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6205681562423706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503422200679779},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.46428051590919495},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.42702195048332214},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37284722924232483},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35412895679473877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35046327114105225},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14471808075904846},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.08676835894584656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07700255513191223},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06356564164161682},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.547","pdf_url":"https://aclanthology.org/2025.acl-long.547.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 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.547","pdf_url":"https://aclanthology.org/2025.acl-long.547.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 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945389.pdf","grobid_xml":"https://content.openalex.org/works/W4412945389.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1546533203","https://openalex.org/W2054080977","https://openalex.org/W1511554945","https://openalex.org/W2015439768","https://openalex.org/W2331316773","https://openalex.org/W4234497699","https://openalex.org/W314221487","https://openalex.org/W2501000359","https://openalex.org/W2137049550","https://openalex.org/W3014989972"],"abstract_inverted_index":{"Multimodal":[0],"reference":[1,39,44,66,91,106,135],"resolution,":[2,92],"including":[3,143],"phrase":[4,118],"grounding,":[5],"aims":[6],"to":[7,34,41,72],"understand":[8],"the":[9,43,138,152],"semantic":[10],"relations":[11,45,136],"between":[12,18,141],"mentions":[13,77],"and":[14,20,37,55,64,75,97,127,145,147],"realworld":[15],"objects.Phrase":[16],"grounding":[17,119],"images":[19],"their":[21,82],"captions":[22],"is":[23,32,167],"a":[24,59],"well-established":[25],"task.In":[26],"contrast,":[27],"for":[28,123],"real-world":[29],"applications,":[30],"it":[31],"essential":[33],"integrate":[35],"textual":[36,63,90,134],"multimodal":[38,65,105],"resolution":[40,67,96,113],"unravel":[42],"within":[46],"dialogue,":[47],"especially":[48],"in":[49,104,116,156],"handling":[50],"ambiguities":[51,153],"caused":[52],"by":[53,68],"pronouns":[54,144],"ellipses.This":[56],"paper":[57],"presents":[58],"framework":[60],"that":[61,88,132,154],"unifies":[62],"mapping":[69],"mention":[70],"embeddings":[71,74],"object":[73],"selecting":[76],"or":[78],"objects":[79],"based":[80],"on":[81],"similarity.":[83],"1":[84,164],"Our":[85],"experiments":[86],"show":[87],"learning":[89],"such":[93],"as":[94],"coreference":[95,112],"predicateargument":[98],"structure":[99],"analysis,":[100],"positively":[101],"affects":[102],"performance":[103],"resolution.In":[107],"particular,":[108],"our":[109],"model":[110],"with":[111],"performs":[114],"better":[115],"pronoun":[117],"than":[120],"representative":[121],"models":[122],"this":[124],"task,":[125],"MDETR":[126],"GLIP.Our":[128],"qualitative":[129],"analysis":[130],"demonstrates":[131],"incorporating":[133],"strengthens":[137],"confidence":[139],"scores":[140],"mentions,":[142],"predicates,":[146],"objects,":[148],"which":[149],"can":[150],"reduce":[151],"arise":[155],"visually":[157],"grounded":[158],"dialogues.*":[159],"Currently":[160],"at":[161],"NEC":[162],"Corporation.":[163],"The":[165],"code":[166],"publicly":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
