{"id":"https://openalex.org/W7160925031","doi":"https://doi.org/10.1007/s10772-026-10265-w","title":"A morphologically annotated dataset and comprehensive evaluation of morphological analyzers for Orani Arabic (MADOran)","display_name":"A morphologically annotated dataset and comprehensive evaluation of morphological analyzers for Orani Arabic (MADOran)","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160925031","doi":"https://doi.org/10.1007/s10772-026-10265-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-026-10265-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-026-10265-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"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":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10772-026-10265-w","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135913781","display_name":"Majdi Sawalha","orcid":"https://orcid.org/0000-0003-4975-6709"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]},{"id":"https://openalex.org/I161913731","display_name":"Al Ain University","ror":"https://ror.org/023abrt21","country_code":"AE","type":"education","lineage":["https://openalex.org/I161913731"]},{"id":"https://openalex.org/I2800358669","display_name":"King Abdullah University Hospital","ror":"https://ror.org/02f6hdc06","country_code":"JO","type":"healthcare","lineage":["https://openalex.org/I2800358669"]}],"countries":["AE","JO"],"is_corresponding":true,"raw_author_name":"Majdi Sawalha","raw_affiliation_strings":["College of Engineering, Al Ain University, Abu Dhabi, United Arab Emirates","Department of Artificial Intelligence, King Abdullah II School of Information Technology, University of Jordan, Amman, Jordan"],"raw_orcid":"https://orcid.org/0000-0003-4975-6709","affiliations":[{"raw_affiliation_string":"College of Engineering, Al Ain University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I161913731"]},{"raw_affiliation_string":"Department of Artificial Intelligence, King Abdullah II School of Information Technology, University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I2800358669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090694041","display_name":"Faisal Alshargi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faisal Alshargi","raw_affiliation_strings":["Amazon Robotics, New York, USA"],"raw_orcid":"https://orcid.org/0009-0005-3359-6052","affiliations":[{"raw_affiliation_string":"Amazon Robotics, New York, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135953754","display_name":"Sane Yagi","orcid":"https://orcid.org/0000-0002-0594-3230"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]},{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE","JO"],"is_corresponding":false,"raw_author_name":"Sane Yagi","raw_affiliation_strings":["Department of English Language and Literature, School of Foreign Languages, University of Jordan, Amman, Jordan","Department of Foreign Languages, University of Sharjah, Sharjah City, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-0594-3230","affiliations":[{"raw_affiliation_string":"Department of English Language and Literature, School of Foreign Languages, University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"Department of Foreign Languages, University of Sharjah, Sharjah City, United Arab Emirates","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015303586","display_name":"Ouafaa Kacha","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ouafaa Kacha","raw_affiliation_strings":["Department of English Language and Literature, School of Foreign Languages, University of Jordan, Amman, Jordan"],"raw_orcid":"https://orcid.org/0009-0005-3933-2082","affiliations":[{"raw_affiliation_string":"Department of English Language and Literature, School of Foreign Languages, University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132834382","display_name":"Abdallah T. AlShdaifat","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]},{"id":"https://openalex.org/I145380033","display_name":"Amman Arab University","ror":"https://ror.org/039xekb14","country_code":"JO","type":"education","lineage":["https://openalex.org/I145380033"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE","JO"],"is_corresponding":false,"raw_author_name":"Abdallah T. AlShdaifat","raw_affiliation_strings":["College of Arts and Humanities, Mohamed bin Zayed University for Humanities, Abu Dhabi, United Arab Emirates","Department of Arabic Language and Literature, School of Arts, University of Jordan, Amman, Jordan"],"raw_orcid":"https://orcid.org/0000-0002-9692-3242","affiliations":[{"raw_affiliation_string":"College of Arts and Humanities, Mohamed bin Zayed University for Humanities, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]},{"raw_affiliation_string":"Department of Arabic Language and Literature, School of Arts, University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I145380033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135963781","display_name":"Mohammad A. Qudah","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]},{"id":"https://openalex.org/I145380033","display_name":"Amman Arab University","ror":"https://ror.org/039xekb14","country_code":"JO","type":"education","lineage":["https://openalex.org/I145380033"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Mohammad A. Qudah","raw_affiliation_strings":["Department of Arabic Language and Literature, School of Arts, University of Jordan, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Arabic Language and Literature, School of Arts, University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I145380033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119749448","display_name":"Najla Alnaqbi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Najla Alnaqbi","raw_affiliation_strings":["College of Arts and Humanities, Mohamed bin Zayed University for Humanities, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7583-2440","affiliations":[{"raw_affiliation_string":"College of Arts and Humanities, Mohamed bin Zayed University for Humanities, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135963575","display_name":"Bayan AbuShawar","orcid":"https://orcid.org/0000-0003-3062-4511"},"institutions":[{"id":"https://openalex.org/I161913731","display_name":"Al Ain University","ror":"https://ror.org/023abrt21","country_code":"AE","type":"education","lineage":["https://openalex.org/I161913731"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Bayan AbuShawar","raw_affiliation_strings":["College of Engineering, Al Ain University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0003-3062-4511","affiliations":[{"raw_affiliation_string":"College of Engineering, Al Ain University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I161913731"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5135913781"],"corresponding_institution_ids":["https://openalex.org/I114972647","https://openalex.org/I161913731","https://openalex.org/I2800358669"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2780},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95686319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.265500009059906,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.265500009059906,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.2045000046491623,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.08699999749660492,"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/annotation","display_name":"Annotation","score":0.7724000215530396},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6959999799728394},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.6191999912261963},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7724000215530396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.703000009059906},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6959999799728394},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6191999912261963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C125496544","wikidata":"https://www.wikidata.org/wiki/Q1422423","display_name":"Arabic languages","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2750999927520752}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-026-10265-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-026-10265-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"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":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-026-10265-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-026-10265-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"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":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8859827518463135,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2342238868","https://openalex.org/W2398594853","https://openalex.org/W2560280095","https://openalex.org/W2572275374","https://openalex.org/W2734322117","https://openalex.org/W2805431570","https://openalex.org/W2886820885","https://openalex.org/W2900897701","https://openalex.org/W2970442528","https://openalex.org/W2978768392","https://openalex.org/W3035390927","https://openalex.org/W3113622461","https://openalex.org/W3133440961","https://openalex.org/W3134591321","https://openalex.org/W4200531534","https://openalex.org/W4310918692","https://openalex.org/W4385569984","https://openalex.org/W4398247955","https://openalex.org/W4414568683"],"related_works":[],"abstract_inverted_index":{"The":[0,69,169],"Orani":[1,50],"dialect":[2,51,141],"of":[3,17,20,52,60,150,222],"Arabic":[4,34,53,155,167],"is":[5],"an":[6],"under-resourced":[7],"Algerian":[8],"language":[9],"variety":[10],"which":[11,174],"also":[12,162],"suffers":[13],"from":[14,95,125],"a":[15,28,44,57,217],"lack":[16],"systematic":[18,58],"evaluation":[19,59],"morphological":[21,61,184],"analyzers.":[22],"This":[23],"study":[24],"attempts":[25],"to":[26,130],"fill":[27],"critical":[29],"resource":[30,170],"gap":[31],"for":[32,48,106,182],"dialectal":[33,132],"NLP,":[35],"linguistic":[36,159],"research,":[37],"and":[38,66,89,91,98,110,114,120,145,152,166,190,204],"educational":[39],"applications.":[40],"It":[41,161],"presents":[42],"MADOran,":[43],"morphologically":[45],"annotated":[46],"corpus":[47],"the":[49,117,121,126,211,226],"(ORN),":[54],"together":[55],"with":[56,216],"analyzers":[62],"across":[63],"conventional,":[64],"deep,":[65],"transformer-based":[67],"approaches.":[68],"dataset":[70],"contains":[71],"30,919":[72],"words":[73],"drawn":[74],"from:":[75],"written":[76],"texts":[77],"(41%)":[78],"on":[79,199,202,206],"topics":[80],"such":[81,136],"as":[82,140],"college":[83],"life,":[84],"culture,":[85],"history,":[86],"humor,":[87],"politics,":[88],"traditions;":[90],"spoken":[92],"material":[93],"(59%)":[94],"storytelling,":[96],"music,":[97],"everyday":[99],"exchanges.":[100],"Each":[101],"token":[102],"received":[103],"manual":[104],"annotation":[105,122],"part-of-speech,":[107],"root,":[108],"pattern,":[109],"glosses":[111],"in":[112,158],"English":[113],"French,":[115],"using":[116],"DIWAN":[118],"tool":[119],"guidelines":[123],"adapted":[124],"Dynamic":[127],"Arabella":[128],"Corpus":[129],"suit":[131],"properties.":[133],"MADOran":[134],"supports":[135],"dialect-focused":[137],"NLP":[138],"tasks":[139],"identification,":[142],"translation,":[143],"generation,":[144],"recognition,":[146],"while":[147],"enabling":[148],"comparison":[149],"ORN":[151],"Modern":[153],"Standard":[154],"(MSA)":[156],"features":[157],"inquiry.":[160],"aids":[163],"lexicographic":[164],"work":[165],"pedagogy.":[168],"observes":[171],"FAIR":[172],"principles,":[173],"ensure":[175],"broad":[176],"reusability.":[177],"Experiments":[178],"demonstrate":[179],"its":[180],"value":[181],"three-head":[183],"analysis":[185],"(POS":[186],"tagging,":[187],"root":[188],"extraction,":[189],"pattern":[191],"recognition).":[192],"A":[193],"CRF":[194],"baseline":[195],"reached":[196],"88.54%":[197],"accuracy":[198,214],"POS,":[200],"87.43%":[201],"roots,":[203],"86.17%":[205],"patterns.":[207],"Fine-tuning":[208],"QARiB":[209],"yielded":[210],"highest":[212],"POS":[213],"(90.04%),":[215],"statistically":[218],"significant":[219],"relative":[220],"gain":[221],"+":[223],"0.88%":[224],"over":[225],"baseline.":[227]},"counts_by_year":[],"updated_date":"2026-05-14T06:09:40.864956","created_date":"2026-05-13T00:00:00"}
