{"id":"https://openalex.org/W4306391222","doi":"https://doi.org/10.1017/s1351324922000444","title":"A benchmark for evaluating Arabic word embedding models","display_name":"A benchmark for evaluating Arabic word embedding models","publication_year":2022,"publication_date":"2022-10-17","ids":{"openalex":"https://openalex.org/W4306391222","doi":"https://doi.org/10.1017/s1351324922000444"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000444","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000444","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5037502713","display_name":"Sane Yagi","orcid":"https://orcid.org/0000-0002-0594-3230"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Sane Yagi","raw_affiliation_strings":["Department of Foreign Languages, University of Sharjah, Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"Department of Foreign Languages, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069884464","display_name":"Ashraf Elnagar","orcid":"https://orcid.org/0000-0003-2265-7268"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Ashraf Elnagar","raw_affiliation_strings":["Department of Computer Science, University of Sharjah, Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065545012","display_name":"Shehdeh Fareh","orcid":"https://orcid.org/0000-0002-1196-9250"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Shehdeh Fareh","raw_affiliation_strings":["Department of Foreign Languages, University of Sharjah, Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"Department of Foreign Languages, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069884464"],"corresponding_institution_ids":["https://openalex.org/I29891158"],"apc_list":null,"apc_paid":null,"fwci":0.6633,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74356423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"4","first_page":"978","last_page":"1003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9952999949455261,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9907000064849854,"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":0.7628816962242126},{"id":"https://openalex.org/keywords/plural","display_name":"Plural","score":0.7101134061813354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6403244733810425},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6026449799537659},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.600580096244812},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5987661480903625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248672366142273},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4163843095302582},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.38931116461753845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628816962242126},{"id":"https://openalex.org/C2779835924","wikidata":"https://www.wikidata.org/wiki/Q146786","display_name":"Plural","level":2,"score":0.7101134061813354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6403244733810425},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6026449799537659},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.600580096244812},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5987661480903625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248672366142273},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4163843095302582},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.38931116461753845},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324922000444","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000444","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1270133036","https://openalex.org/W1600700896","https://openalex.org/W1614298861","https://openalex.org/W1949981797","https://openalex.org/W2251176673","https://openalex.org/W2460442863","https://openalex.org/W2483215953","https://openalex.org/W2581256107","https://openalex.org/W2740654950","https://openalex.org/W2743040064","https://openalex.org/W2767784948","https://openalex.org/W2770803436","https://openalex.org/W2783122809","https://openalex.org/W2787956672","https://openalex.org/W2803176955","https://openalex.org/W2890269216","https://openalex.org/W2900975931","https://openalex.org/W2901770030","https://openalex.org/W2948589047","https://openalex.org/W2954275542","https://openalex.org/W2971156525","https://openalex.org/W2974335209","https://openalex.org/W2975214639","https://openalex.org/W2991506583","https://openalex.org/W2992999841","https://openalex.org/W2999262142","https://openalex.org/W3011353546","https://openalex.org/W3013547323","https://openalex.org/W3036520662","https://openalex.org/W3046205772","https://openalex.org/W3095369918","https://openalex.org/W3111704875","https://openalex.org/W3120314993","https://openalex.org/W3128072365","https://openalex.org/W3130792169","https://openalex.org/W3135702410","https://openalex.org/W3196771354","https://openalex.org/W3210486066","https://openalex.org/W3216452752","https://openalex.org/W4390864827","https://openalex.org/W6748355100","https://openalex.org/W6804884774","https://openalex.org/W6860256207"],"related_works":["https://openalex.org/W2316639949","https://openalex.org/W3118844042","https://openalex.org/W1976158732","https://openalex.org/W2428547322","https://openalex.org/W3186444185","https://openalex.org/W2380671354","https://openalex.org/W2809112224","https://openalex.org/W1506357412","https://openalex.org/W2910519869","https://openalex.org/W2624155477"],"abstract_inverted_index":{"Abstract":[0],"Modelling":[1],"the":[2,40,75,89,113,139,155,164,188,237,241,261,283,286],"distributional":[3,38],"semantics":[4,207],"of":[5,116,138,154,160,163,212,230,239,248,292,299],"such":[6,36,108],"a":[7,59,78,105,246],"morphologically":[8,294],"rich":[9,295],"language":[10,269,296],"as":[11,217,219],"Arabic":[12,49,71,272],"needs":[13],"to":[14,64,150,282],"take":[15],"into":[16],"account":[17],"its":[18,28],"introflexive,":[19],"fusional,":[20],"and":[21,31,72,83,118,121,126,129,132,135,167,178,187,194,198,205,210,215,222,233,264,276,297],"inflectional":[22,122],"nature":[23],"attributes":[24],"that":[25,42,61,109,285],"make":[26],"up":[27],"combinatorial":[29],"sequences":[30],"substitutional":[32],"paradigms.":[33],"To":[34],"evaluate":[35],"word":[37,300],"models,":[39],"benchmarks":[41],"have":[43,50],"been":[44],"used":[45],"thus":[46],"far":[47],"in":[48,53,68,99,104,144,190],"mimicked":[51],"those":[52],"English.":[54],"This":[55],"paper":[56],"reports":[57],"on":[58],"benchmark":[60,101,146,158,263,288],"we":[62,97,244,256],"designed":[63],"reflect":[65],"linguistic":[66],"patterns":[67,128,172],"both":[69],"Contemporary":[70],"Classical":[73],"Arabic,":[74,87],"first":[76],"being":[77],"cover":[79],"term":[80],"for":[81,91,202],"written":[82],"spoken":[84],"Modern":[85],"Standard":[86],"while":[88],"second":[90],"pre-modern":[92],"Arabic.":[93],"The":[94,157,279],"analogy":[95],"items":[96],"included":[98,143],"this":[100,145,293],"are":[102,147],"chosen":[103],"transparent":[106],"manner":[107],"they":[110],"would":[111],"capture":[112],"major":[114],"features":[115],"nouns":[117],"verbs;":[119],"derivational":[120],"morphology;":[123],"high-,":[124,231],"middle-,":[125],"low-frequency":[127,234],"lexical":[130,206],"items;":[131],"morphosemantic,":[133],"morphosyntactic,":[134],"semantic":[136],"dimensions":[137],"language.":[140,156],"All":[141,224],"categories":[142,225],"carefully":[148],"selected":[149],"ensure":[151],"proper":[152],"representation":[153],"consists":[159],"45":[161],"roots":[162],"trilateral,":[165],"all-consonantal,":[166],"semivowel-inclusive":[168],"types;":[169],"six":[170],"morphosemantic":[171],"(\u2019af\u2018ala;":[173],"ifta\u2018ala;":[174],"infa\u2018ala;":[175],"istaf\u2018ala;":[176],"tafa\u2018\u2018ala;":[177],"taf\u0101\u2018ala);":[179],"five":[180],"derivations":[181],"(the":[182],"verbal":[183],"noun,":[184],"active":[185],"participle,":[186],"contrasts":[189],"Masculine-Feminine;":[191],"Feminine-Singular-Plural;":[192],"Masculine-Singular-Plural);":[193],"morphosyntactic":[195],"transformations":[196],"(perfect":[197],"imperfect":[199],"verbs":[200],"conjugated":[201],"all":[203],"pronouns);":[204],"(synonyms,":[208],"antonyms,":[209],"hyponyms":[211],"nouns,":[213],"verbs,":[214],"adjectives),":[216],"well":[218],"capital":[220],"cities":[221],"currencies.":[223],"include":[226],"an":[227],"equal":[228],"proportion":[229],"medium-,":[232],"items.":[235],"For":[236],"purpose":[238],"validating":[240],"proposed":[242,262,287],"benchmark,":[243],"developed":[245],"set":[247],"embedding":[249],"models":[250],"from":[251],"different":[252],"textual":[253],"sources.":[254],"Then,":[255],"tested":[257],"them":[258],"intrinsically":[259],"using":[260,266],"extrinsically":[265],"two":[267],"natural":[268],"processing":[270],"tasks:":[271],"Named":[273],"Entity":[274],"Recognition":[275],"Text":[277],"Classification.":[278],"evaluation":[280],"leads":[281],"conclusion":[284],"is":[289],"truly":[290],"reflective":[291],"discriminatory":[298],"embeddings.":[301]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
