{"id":"https://openalex.org/W7166801738","doi":"https://doi.org/10.18653/v1/2026.acl-long.91","title":"AraVQA: Building a New Arabic Factoid Visual Question Answering Dataset from Wikipedia","display_name":"AraVQA: Building a New Arabic Factoid Visual Question Answering Dataset from Wikipedia","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166801738","doi":"https://doi.org/10.18653/v1/2026.acl-long.91"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.91","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.91","pdf_url":"https://aclanthology.org/2026.acl-long.91.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.91.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023462766","display_name":"Sultan Alrowili","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sultan Alrowili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086381528","display_name":"Younes Samih","orcid":"https://orcid.org/0000-0002-0485-7920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Younes Samih","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087143068","display_name":"Abed Alhakim Freihat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abed Alhakim Freihat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057946149","display_name":"Mathan K. Eswaran","orcid":"https://orcid.org/0009-0008-2754-6122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathan Kumar Eswaran","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":0.85720184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2026","last_page":"2042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9121999740600586,"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":0.9121999740600586,"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/T10028","display_name":"Topic Modeling","score":0.031300000846385956,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.011699999682605267,"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/question-answering","display_name":"Question answering","score":0.8108999729156494},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.41350001096725464},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3644999861717224},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.26260000467300415}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8108999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257999777793884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5609999895095825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C62360110","wikidata":"https://www.wikidata.org/wiki/Q96777007","display_name":"Circumscription","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.91","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.91","pdf_url":"https://aclanthology.org/2026.acl-long.91.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.91","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.91","pdf_url":"https://aclanthology.org/2026.acl-long.91.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166801738.pdf","grobid_xml":"https://content.openalex.org/works/W7166801738.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,18,117],"large-scale":[3],"Visual":[4,81,119],"Question":[5,82],"Answering":[6,83],"(VQA)":[7],"datasets":[8,23],"has":[9],"traditionally":[10],"relied":[11],"on":[12,25,123],"resource-intensive":[13],"manual":[14,139],"annotation.In":[15],"addition,":[16],"most":[17,77],"the":[19,45,56,76,115],"existing":[20,118,149],"Arabic":[21,79,98,124,146,150],"VQA":[22,125,151],"focus":[24],"culturally-specific":[26],"and":[27,90,136],"dialect-aware":[28],"domains.To":[29],"address":[30],"these":[31],"limitations,":[32],"we":[33,72,127],"propose":[34],"a":[35,64,110,129],"new":[36,65],"pipeline":[37],"that":[38,104,141],"leverages":[39],"Wikipedia":[40],"template":[41],"tags":[42],"to":[43,61,113,145],"extract":[44],"relevant":[46],"information":[47],"for":[48],"each":[49],"image,":[50],"which":[51],"is":[52],"subsequently":[53],"utilized":[54],"by":[55],"Large":[57],"Language":[58,120],"Model":[59],"(LLM)":[60],"synthetically":[62],"generate":[63],"visual":[66],"question":[67],"answering":[68],"dataset.Using":[69],"this":[70],"pipeline,":[71],"have":[73],"constructed":[74],"AraVQA,":[75],"comprehensive":[78],"Factoid":[80],"dataset,":[84],"containing":[85],"more":[86,143],"than":[87,148],"50,000":[88],"questions":[89],"covering":[91],"over":[92],"20":[93],"varied":[94],"primary":[95],"subjects":[96],"within":[97],"general":[99],"knowledge.Our":[100],"detailed":[101],"analysis":[102],"shows":[103],"our":[105,134],"dataset":[106,112,135],"can":[107],"serve":[108],"as":[109],"post-training":[111],"enhance":[114],"performance":[116],"Models":[121],"(VLMs)":[122],"tasks.Furthermore,":[126],"present":[128],"novel":[130],"benchmark,":[131],"derived":[132],"from":[133],"validated":[137],"through":[138],"annotation,":[140],"poses":[142],"challenges":[144],"VLMs":[147],"datasets.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}