{"id":"https://openalex.org/W4415428234","doi":"https://doi.org/10.3233/faia251306","title":"Assessing and Improving the Multilingual Visual Word Sense Disambiguation Ability of Vision-Language Models","display_name":"Assessing and Improving the Multilingual Visual Word Sense Disambiguation Ability of Vision-Language Models","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428234","doi":"https://doi.org/10.3233/faia251306"},"language":"en","primary_location":{"id":"doi:10.3233/faia251306","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251306","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251306","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092867319","display_name":"Elio Musacchio","orcid":"https://orcid.org/0009-0006-9670-9998"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["CA","IT"],"is_corresponding":false,"raw_author_name":"Elio Musacchio","raw_affiliation_strings":["Department of Computer Science, University of Bari Aldo Moro, Italy","University of Pisa, Italian National PhD Program in Artificial Intelligence"],"raw_orcid":"https://orcid.org/0009-0006-9670-9998","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bari Aldo Moro, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"University of Pisa, Italian National PhD Program in Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010854767","display_name":"Lucia Siciliani","orcid":"https://orcid.org/0000-0002-1438-280X"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lucia Siciliani","raw_affiliation_strings":["Department of Computer Science, University of Bari Aldo Moro, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1438-280X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bari Aldo Moro, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070784701","display_name":"Pierpaolo Basile","orcid":"https://orcid.org/0000-0002-0545-1105"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pierpaolo Basile","raw_affiliation_strings":["Department of Computer Science, University of Bari Aldo Moro, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0545-1105","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bari Aldo Moro, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059814300","display_name":"Giovanni Semeraro","orcid":"https://orcid.org/0000-0001-6883-1853"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Semeraro","raw_affiliation_strings":["Department of Computer Science, University of Bari Aldo Moro, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6883-1853","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bari Aldo Moro, Italy","institution_ids":["https://openalex.org/I5561750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43938387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7829999923706055,"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":0.7829999923706055,"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/T13382","display_name":"Robotics and Automated Systems","score":0.7348999977111816,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7254999876022339,"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/generalization","display_name":"Generalization","score":0.6417999863624573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6248999834060669},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5950999855995178},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5044000148773193},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.5044000148773193},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4812999963760376},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.4629000127315521},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6600000262260437},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341000199317932},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.5044000148773193},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.4629000127315521},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3756999969482422},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia251306","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251306","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:ricerca.uniba.it:11586/556689","is_oa":true,"landing_page_url":"https://ebooks.iospress.nl/volumearticle/76242","pdf_url":null,"source":{"id":"https://openalex.org/S4377196296","display_name":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5561750","host_organization_name":"University of Bari Aldo Moro","host_organization_lineage":["https://openalex.org/I5561750"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia251306","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251306","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"multimodal":[6,100],"understanding.":[7],"Due":[8],"to":[9,31,59,88],"their":[10,57],"extensive":[11],"training,":[12],"they":[13],"excel":[14],"in":[15],"tasks":[16],"such":[17],"as":[18],"visual":[19],"question":[20],"answering":[21],"and":[22,34,95,102],"image":[23,63],"retrieval.":[24],"Their":[25],"impressive":[26],"generalization":[27],"ability":[28,58,85],"enables":[29],"them":[30],"address":[32],"novel":[33],"complex":[35],"challenges.":[36],"In":[37],"this":[38,90],"study,":[39],"we":[40,55,82],"evaluate":[41,83],"the":[42,47,61,84,97],"capability":[43],"of":[44,67,86,99],"VLMs":[45,87],"for":[46,69],"Visual":[48],"Word":[49],"Sense":[50],"Disambiguation":[51],"(VWSD)":[52],"task.":[53],"Specifically,":[54],"examine":[56],"select":[60],"correct":[62],"from":[64],"a":[65,70],"set":[66],"candidates":[68],"given":[71],"lemma":[72],"based":[73],"on":[74],"minimal":[75],"contextual":[76],"information":[77],"(few":[78],"additional":[79],"words).":[80],"Additionally,":[81],"solve":[89],"task":[91],"across":[92],"multiple":[93],"languages":[94],"analyze":[96],"performance":[98],"encoder-based":[101],"generative":[103],"VLMs.":[104]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}
