{"id":"https://openalex.org/W4400528237","doi":"https://doi.org/10.1145/3626772.3657889","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","display_name":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400528237","doi":"https://doi.org/10.1145/3626772.3657889"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657889","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064852810","display_name":"Abdelrahman Abdallah","orcid":"https://orcid.org/0000-0001-8747-4927"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Abdelrahman Abdallah","raw_affiliation_strings":["University of Innsbruck, Innsbruck, Tyrol, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Innsbruck, Tyrol, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083805180","display_name":"Mahmoud SalahEldin Kasem","orcid":"https://orcid.org/0000-0002-8513-570X"},"institutions":[{"id":"https://openalex.org/I91041137","display_name":"Assiut University","ror":"https://ror.org/01jaj8n65","country_code":"EG","type":"education","lineage":["https://openalex.org/I91041137"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mahmoud Kasem","raw_affiliation_strings":["Assuit University, Assuit, Egypt"],"affiliations":[{"raw_affiliation_string":"Assuit University, Assuit, Egypt","institution_ids":["https://openalex.org/I91041137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114778014","display_name":"Mahmoud Abdalla","orcid":"https://orcid.org/0000-0002-4270-2268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahmoud Abdalla","raw_affiliation_strings":["DISCO AI, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"DISCO AI, Cairo, Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108131764","display_name":"Mohamed Mahmoud","orcid":"https://orcid.org/0000-0001-6764-8969"},"institutions":[{"id":"https://openalex.org/I91041137","display_name":"Assiut University","ror":"https://ror.org/01jaj8n65","country_code":"EG","type":"education","lineage":["https://openalex.org/I91041137"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohamed Mahmoud","raw_affiliation_strings":["Assuit University, Assuit, Egypt"],"affiliations":[{"raw_affiliation_string":"Assuit University, Assuit, Egypt","institution_ids":["https://openalex.org/I91041137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103324310","display_name":"Mohamed Elkasaby","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Elkasaby","raw_affiliation_strings":["DISCO AI, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"DISCO AI, Cairo, Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092905627","display_name":"Yasser Elbendary","orcid":"https://orcid.org/0009-0001-0963-5024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasser Elbendary","raw_affiliation_strings":["DISCO AI, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"DISCO AI, Cairo, Egypt","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["University of Innsbruck, Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5064852810"],"corresponding_institution_ids":["https://openalex.org/I190249584"],"apc_list":null,"apc_paid":null,"fwci":7.2978,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97527143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2049","last_page":"2059"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.991599977016449,"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/arabic","display_name":"Arabic","score":0.796455442905426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402271628379822},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7158348560333252},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6324559450149536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5007171630859375},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4291422367095947},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2822779417037964},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04924628138542175}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.796455442905426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402271628379822},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7158348560333252},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6324559450149536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007171630859375},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4291422367095947},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2822779417037964},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04924628138542175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657889","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W82374267","https://openalex.org/W1516184288","https://openalex.org/W1973529378","https://openalex.org/W2033047024","https://openalex.org/W2113908378","https://openalex.org/W2121300346","https://openalex.org/W2125436846","https://openalex.org/W2251818205","https://openalex.org/W2431106835","https://openalex.org/W2515224663","https://openalex.org/W2742229469","https://openalex.org/W2901059163","https://openalex.org/W2912924812","https://openalex.org/W2953343412","https://openalex.org/W2963929190","https://openalex.org/W2963963993","https://openalex.org/W2964223283","https://openalex.org/W2970960342","https://openalex.org/W3027495661","https://openalex.org/W3027879771","https://openalex.org/W3080820686","https://openalex.org/W3102882607","https://openalex.org/W3128268873","https://openalex.org/W3149627794","https://openalex.org/W3171930167","https://openalex.org/W4225711758","https://openalex.org/W4281758439","https://openalex.org/W4284689799","https://openalex.org/W4284691483","https://openalex.org/W4311183537","https://openalex.org/W4383605243","https://openalex.org/W4385474609","https://openalex.org/W4385569757","https://openalex.org/W4385570777","https://openalex.org/W4385780698","https://openalex.org/W4385782731","https://openalex.org/W6831684532"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,118],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,18,71,79,87,114,123,135],"significant":[6,132],"gap":[7],"in":[8,30,63,113,127,134],"Arabic":[9,64,80,91,106,115,128,138],"natural":[10],"language":[11,102,116],"processing":[12],"(NLP)":[13],"resources":[14],"by":[15,44],"introducing":[16],"ArabicaQA,":[17,120],"first":[19,72],"large-scale":[20],"dataset":[21,141],"for":[22,105,147],"machine":[23],"reading":[24],"comprehension":[25],"and":[26,39,122,142],"open-domain":[27,57],"question":[28,107,129],"answering":[29,130],"Arabic.":[31],"This":[32],"comprehensive":[33],"dataset,":[34],"consisting":[35],"of":[36,56,90,100,125,137],"89,095":[37],"answerable":[38,50],"3,701":[40],"unanswerable":[41],"questions":[42,58],"created":[43],"crowdworkers":[45],"to":[46,49,85],"look":[47],"similar":[48],"ones,":[51],"along":[52],"with":[53],"additional":[54],"labels":[55],"marks":[59],"a":[60],"crucial":[61],"advancement":[62],"NLP":[65],"resources.":[66],"We":[67],"also":[68],"present":[69],"AraDPR,":[70,121],"dense":[73],"passage":[74],"retrieval":[75],"model":[76],"trained":[77],"on":[78],"Wikipedia":[81],"corpus,":[82],"specifically":[83],"designed":[84],"tackle":[86],"unique":[88],"challenges":[89],"text":[92],"retrieval.":[93],"Furthermore,":[94],"our":[95],"study":[96],"includes":[97],"extensive":[98],"benchmarking":[99,124],"large":[101],"models":[103],"(LLMs)":[104],"answering,":[108],"critically":[109],"evaluating":[110],"their":[111],"performance":[112],"context.":[117],"conclusion,":[119],"LLMs":[126],"offer":[131],"advancements":[133],"field":[136],"NLP.":[139],"The":[140],"code":[143],"are":[144],"publicly":[145],"accessible":[146],"further":[148],"research":[149],"https://github.com/DataScienceUIBK/ArabicaQA.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
