{"id":"https://openalex.org/W4385572940","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.34","title":"Learning From Arabic Corpora But Not Always From Arabic Speakers: A Case Study of the Arabic Wikipedia Editions","display_name":"Learning From Arabic Corpora But Not Always From Arabic Speakers: A Case Study of the Arabic Wikipedia Editions","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572940","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.34"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.34","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.34","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.34","pdf_url":"https://aclanthology.org/2022.wanlp-1.34.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.wanlp-1.34.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065099281","display_name":"Saied Alshahrani","orcid":"https://orcid.org/0009-0007-1867-4627","observed_orcids":["https://orcid.org/0009-0007-1867-4627"]},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saied Alshahrani","raw_affiliation_strings":["Department of Computer Science Clarkson University, Potsdam, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010621136","display_name":"Esma Wali","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Esma Wali","raw_affiliation_strings":["Department of Computer Science Clarkson University, Potsdam, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070197299","display_name":"Jeanna Neefe Matthews","orcid":"https://orcid.org/0000-0001-5955-0996","observed_orcids":["https://orcid.org/0000-0001-5955-0996"]},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeanna Matthews","raw_affiliation_strings":["Department of Computer Science Clarkson University, Potsdam, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010621136"],"corresponding_institution_ids":["https://openalex.org/I16944753"],"apc_list":null,"apc_paid":null,"fwci":0.4144,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62362254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9223999977111816,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9223999977111816,"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":0.054499998688697815,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.00989999994635582,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic-wikipedia","display_name":"Arabic Wikipedia","score":0.9359999895095825},{"id":"https://openalex.org/keywords/egyptian-arabic","display_name":"Egyptian Arabic","score":0.6200000047683716},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.9210000038146973},{"id":"https://openalex.org/keywords/moroccan-arabic","display_name":"Moroccan Arabic","score":0.9729999899864197},{"id":"https://openalex.org/keywords/training-data-bias","display_name":"training data bias","score":0.5669999718666077},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6119999885559082},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.3889999985694885},{"id":"https://openalex.org/keywords/automatic-content-generation","display_name":"automated content generation","score":0.7630000114440918},{"id":"https://openalex.org/keywords/arabic-corpus","display_name":"Arabic corpus","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107402324676514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7147551774978638},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5990337133407593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936799049377441},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5600138902664185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.450484037399292},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43293625116348267},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27368927001953125},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.22936812043190002},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.wanlp-1.34","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.34","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.34","pdf_url":"https://aclanthology.org/2022.wanlp-1.34.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wanlp-1.34","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.34","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.34","pdf_url":"https://aclanthology.org/2022.wanlp-1.34.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572940.pdf","grobid_xml":"https://content.openalex.org/works/W4385572940.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W137989762","https://openalex.org/W181901128","https://openalex.org/W1566289585","https://openalex.org/W1975094859","https://openalex.org/W1984708705","https://openalex.org/W2098603082","https://openalex.org/W2134285054","https://openalex.org/W2137397532","https://openalex.org/W2156554947","https://openalex.org/W2164503643","https://openalex.org/W2250378459","https://openalex.org/W2250732891","https://openalex.org/W2251882277","https://openalex.org/W2556053680","https://openalex.org/W2579146096","https://openalex.org/W2787560479","https://openalex.org/W2890931798","https://openalex.org/W2893425640","https://openalex.org/W2896457183","https://openalex.org/W2897042519","https://openalex.org/W2911227954","https://openalex.org/W2911599914","https://openalex.org/W2923014074","https://openalex.org/W2950018712","https://openalex.org/W2970476646","https://openalex.org/W3023547440","https://openalex.org/W3030163527","https://openalex.org/W3041109217","https://openalex.org/W3043315258","https://openalex.org/W3110173662","https://openalex.org/W3133702157","https://openalex.org/W3133979110","https://openalex.org/W3135371071","https://openalex.org/W3135747027","https://openalex.org/W3138919075","https://openalex.org/W3145971126","https://openalex.org/W3154199344","https://openalex.org/W3185259833","https://openalex.org/W3191132518","https://openalex.org/W3214193653","https://openalex.org/W3217358679","https://openalex.org/W4225836653","https://openalex.org/W4235023933","https://openalex.org/W4249194216","https://openalex.org/W4312232820","https://openalex.org/W4320725107"],"related_works":["https://openalex.org/W4389518175","https://openalex.org/W6902310750","https://openalex.org/W7131780456","https://openalex.org/W4404781483","https://openalex.org/W7140100493","https://openalex.org/W1985583527","https://openalex.org/W128151686","https://openalex.org/W2047949232","https://openalex.org/W7166578021","https://openalex.org/W4389492793"],"abstract_inverted_index":{"Wikipedia":[0,71,107,123,171],"is":[1,31,83,180],"a":[2,16,51,97],"common":[3],"source":[4,17],"of":[5,44,129,145,164],"training":[6],"data":[7],"for":[8,18,25,184],"Natural":[9],"Language":[10,147],"Processing":[11],"(NLP)":[12],"research,":[13],"especially":[14],"as":[15],"corpora":[19,40,69,186],"in":[20,50,119],"languages":[21,59],"other":[22,58,63],"than":[23],"English.However,":[24],"many":[26,48],"downstream":[27],"NLP":[28],"tasks,":[29],"it":[30,82],"important":[32,84],"to":[33,37,85,188],"understand":[34,86],"the":[35,105,120,141,158,167,182],"degree":[36],"which":[38],"these":[39,152,175],"reflect":[41],"representative":[42],"contributions":[43],"native":[45,165],"speakers.In":[46],"particular,":[47,115],"entries":[49],"given":[52],"language":[53],"may":[54],"be":[55],"translated":[56],"from":[57,132,151],"or":[60],"produced":[61],"through":[62],"automated":[64],"mechanisms.Language":[65],"models":[66,155],"built":[67],"using":[68],"like":[70],"can":[72],"embed":[73],"history,":[74],"culture,":[75],"bias,":[76],"stereotypes,":[77],"politics,":[78],"and":[79,113,127,143,161],"more,":[80],"but":[81,177],"whose":[87],"views":[88],"are":[89],"actually":[90],"being":[91],"represented.In":[92],"this":[93,179],"paper,":[94],"we":[95,116],"present":[96],"case":[98,183],"study":[99],"focusing":[100],"specifically":[101],"on":[102],"differences":[103],"among":[104],"Arabic":[106,122],"editions":[108],"(Modern":[109],"Standard":[110],"Arabic,":[111],"Egyptian,":[112],"Moroccan).In":[114],"document":[117],"issues":[118,137],"Egyptian":[121],"with":[124],"automatic":[125],"creation/generation":[126],"translation":[128],"content":[130],"pages":[131],"English":[133],"without":[134],"human":[135],"supervision.These":[136],"could":[138],"substantially":[139],"affect":[140],"performance":[142],"accuracy":[144],"Large":[146],"Models":[148],"(LLMs)":[149],"trained":[150],"corpora,":[153],"producing":[154],"that":[156],"lack":[157],"cultural":[159],"richness":[160],"meaningful":[162],"representation":[163],"speakers.Fortunately,":[166],"metadata":[168],"maintained":[169],"by":[170],"provides":[172],"visibility":[173],"into":[174],"issues,":[176],"unfortunately,":[178],"not":[181],"all":[185],"used":[187],"train":[189],"LLMs.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}