{"id":"https://openalex.org/W3011500873","doi":"https://doi.org/10.1109/aiccsa47632.2019.9035212","title":"KUNUZ: A Multi-Purpose Reusable Test Collection for Classical Arabic Document Engineering","display_name":"KUNUZ: A Multi-Purpose Reusable Test Collection for Classical Arabic Document Engineering","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011500873","doi":"https://doi.org/10.1109/aiccsa47632.2019.9035212","mag":"3011500873"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa47632.2019.9035212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa47632.2019.9035212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA)","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/A5058227632","display_name":"Ibrahim Bounhas","orcid":"https://orcid.org/0000-0002-6310-7062"},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]},{"id":"https://openalex.org/I179097149","display_name":"University of Carthage","ror":"https://ror.org/057x6za15","country_code":"TN","type":"education","lineage":["https://openalex.org/I179097149"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Ibrahim Bounhas","raw_affiliation_strings":["Higher Institute of Documentation, La Manouba University, Tunisia","JARIR: Joint group for Artificial Reasoning and Information Retrieval","LISI: Laboratory of Computer science for industrial systems, Carthage University, Tunisia"],"affiliations":[{"raw_affiliation_string":"Higher Institute of Documentation, La Manouba University, Tunisia","institution_ids":["https://openalex.org/I83259278"]},{"raw_affiliation_string":"JARIR: Joint group for Artificial Reasoning and Information Retrieval","institution_ids":[]},{"raw_affiliation_string":"LISI: Laboratory of Computer science for industrial systems, Carthage University, Tunisia","institution_ids":["https://openalex.org/I179097149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006846421","display_name":"Souheila Ben Guirat","orcid":"https://orcid.org/0000-0002-6679-3731"},"institutions":[{"id":"https://openalex.org/I179097149","display_name":"University of Carthage","ror":"https://ror.org/057x6za15","country_code":"TN","type":"education","lineage":["https://openalex.org/I179097149"]},{"id":"https://openalex.org/I176902721","display_name":"Carthage College","ror":"https://ror.org/00wkay776","country_code":"US","type":"education","lineage":["https://openalex.org/I176902721"]}],"countries":["TN","US"],"is_corresponding":false,"raw_author_name":"Souheila Ben Guirat","raw_affiliation_strings":["LISI: Laboratory of Computer Science for Industrial Systems, Carthage University"],"affiliations":[{"raw_affiliation_string":"LISI: Laboratory of Computer Science for Industrial Systems, Carthage University","institution_ids":["https://openalex.org/I176902721","https://openalex.org/I179097149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058227632"],"corresponding_institution_ids":["https://openalex.org/I179097149","https://openalex.org/I83259278"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60560393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9958999752998352,"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":0.8241461515426636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6782000064849854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987098217010498},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5980139374732971},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5724620819091797},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5589651465415955},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.545916736125946},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5066526532173157},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5063883066177368},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.495369553565979},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.47354382276535034},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44373929500579834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4150822162628174},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12841591238975525},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10657468438148499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241461515426636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6782000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987098217010498},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5980139374732971},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5724620819091797},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5589651465415955},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.545916736125946},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5066526532173157},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5063883066177368},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.495369553565979},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.47354382276535034},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44373929500579834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4150822162628174},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12841591238975525},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10657468438148499},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa47632.2019.9035212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa47632.2019.9035212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA)","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":66,"referenced_works":["https://openalex.org/W57662518","https://openalex.org/W116243914","https://openalex.org/W122372052","https://openalex.org/W1161157532","https://openalex.org/W1490890048","https://openalex.org/W1545305210","https://openalex.org/W1552863221","https://openalex.org/W1558740192","https://openalex.org/W1583061999","https://openalex.org/W1794998906","https://openalex.org/W1968067123","https://openalex.org/W1981685568","https://openalex.org/W1982091206","https://openalex.org/W1993501158","https://openalex.org/W2005615872","https://openalex.org/W2011677228","https://openalex.org/W2051834357","https://openalex.org/W2094110868","https://openalex.org/W2097341304","https://openalex.org/W2097670688","https://openalex.org/W2098700435","https://openalex.org/W2106525823","https://openalex.org/W2110161737","https://openalex.org/W2132454076","https://openalex.org/W2143157562","https://openalex.org/W2144810223","https://openalex.org/W2147272182","https://openalex.org/W2153846790","https://openalex.org/W2155482025","https://openalex.org/W2157791002","https://openalex.org/W2181580069","https://openalex.org/W2183973956","https://openalex.org/W2184157602","https://openalex.org/W2187807684","https://openalex.org/W2240315349","https://openalex.org/W2250816155","https://openalex.org/W2327415498","https://openalex.org/W2523251022","https://openalex.org/W2572487044","https://openalex.org/W2737716763","https://openalex.org/W2757881267","https://openalex.org/W2792575422","https://openalex.org/W2890273195","https://openalex.org/W2915610764","https://openalex.org/W2997918148","https://openalex.org/W2998768810","https://openalex.org/W3004533406","https://openalex.org/W3211624502","https://openalex.org/W4249836992","https://openalex.org/W4252076394","https://openalex.org/W4285719527","https://openalex.org/W6603191899","https://openalex.org/W6604620317","https://openalex.org/W6604885153","https://openalex.org/W6633134671","https://openalex.org/W6647288420","https://openalex.org/W6679833840","https://openalex.org/W6681182635","https://openalex.org/W6681530644","https://openalex.org/W6682953061","https://openalex.org/W6686210931","https://openalex.org/W6687095889","https://openalex.org/W6691525129","https://openalex.org/W6741802111","https://openalex.org/W6815002142","https://openalex.org/W6922397407"],"related_works":["https://openalex.org/W2783003676","https://openalex.org/W2620283452","https://openalex.org/W4392318734","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W2801712537","https://openalex.org/W4396221470","https://openalex.org/W587642979","https://openalex.org/W2894059694","https://openalex.org/W4299493485"],"abstract_inverted_index":{"Corpora":[0],"are":[1,80],"important":[2],"resources":[3,31],"for":[4,62],"several":[5,66],"applications":[6,64],"in":[7,65,83,109,138],"Information":[8],"Retrieval":[9],"(IR)":[10],"and":[11,49,75,90,105,122,134],"Knowledge":[12],"Extraction":[13],"(KE).":[14],"Arabic":[15,29,36,52],"is":[16,56,97],"a":[17,42,59,159],"low":[18],"resourced":[19],"language":[20,30],"characterized":[21],"by":[22],"its":[23],"complex":[24],"morphology.":[25],"Furthermore,":[26],"most":[27],"existent":[28],"focus":[32],"on":[33,158],"Modern":[34],"Standard":[35],"(MSA).":[37],"This":[38],"paper":[39],"describes":[40,114],"KUNUZ":[41],"multi-purpose":[43],"test":[44],"collection":[45],"composed":[46],"of":[47,68,117,130,147],"voweled":[48],"structured":[50],"classical":[51],"documents.":[53],"Its":[54],"goal":[55],"to":[57,85,143,153],"provide":[58],"unique":[60],"benchmark":[61],"assessing":[63],"areas":[67],"document":[69,73],"engineering":[70],"including":[71],"IR,":[72],"classification":[74],"information":[76],"extraction.":[77],"The":[78,112],"documents":[79],"also":[81,126,151],"translated":[82],"English":[84],"allow":[86],"Arabic-English":[87],"cross-lingual":[88],"IR":[89,96,135],"machine":[91],"translation.":[92],"As":[93],"far":[94],"as":[95],"concerned,":[98],"we":[99,150],"follow":[100],"the":[101,115,128,139,145,155],"standard":[102],"topic":[103,118],"development":[104],"results":[106,120,129,146,156],"sampling":[107],"used":[108,137],"international":[110],"campaigns.":[111],"paper,":[113],"process":[116],"development,":[119],"pooling":[121],"relevance":[123],"judgment.":[124],"It":[125],"analyses":[127],"some":[131],"processing":[132],"tools":[133],"models":[136],"runs.":[140],"In":[141],"order":[142],"enhance":[144],"our":[148],"experiments,":[149],"proposed":[152],"combine":[154],"based":[157],"meta-search":[160],"approach":[161],"using":[162],"Support":[163],"Vector":[164],"Machines":[165],"(SVM)":[166],"classification.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
