{"id":"https://openalex.org/W4402671397","doi":"https://doi.org/10.18653/v1/2024.arabicnlp-1.14","title":"AlclaM: Arabic Dialect Language Model","display_name":"AlclaM: Arabic Dialect Language Model","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671397","doi":"https://doi.org/10.18653/v1/2024.arabicnlp-1.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.arabicnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.arabicnlp-1.14","pdf_url":"https://aclanthology.org/2024.arabicnlp-1.14.pdf","source":null,"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 Second Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.arabicnlp-1.14.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087283637","display_name":"Murtadha Ahmed","orcid":"https://orcid.org/0000-0002-0741-0710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murtadha Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042097351","display_name":"Saghir Alfasly","orcid":"https://orcid.org/0000-0002-8561-660X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saghir Alfasly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011332528","display_name":"Bo Wen","orcid":"https://orcid.org/0000-0003-2261-3150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107544622","display_name":"Jamal Addeen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jamal Addeen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108152841","display_name":"Mohammed Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100357482","display_name":"Yunfeng Liu","orcid":"https://orcid.org/0000-0002-4536-8138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfeng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7136,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98707726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9803000092506409,"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":0.9803000092506409,"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/T14210","display_name":"Historical and Linguistic Studies","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T14037","display_name":"Arabic Language Education Studies","score":0.9340999722480774,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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","display_name":"Arabic","score":0.793574869632721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7185438871383667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5940451622009277},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5777354836463928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4424579441547394},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08417382836341858}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.793574869632721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185438871383667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5940451622009277},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5777354836463928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424579441547394},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08417382836341858}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.arabicnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.arabicnlp-1.14","pdf_url":"https://aclanthology.org/2024.arabicnlp-1.14.pdf","source":null,"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 Second Arabic Natural Language Processing Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.arabicnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.arabicnlp-1.14","pdf_url":"https://aclanthology.org/2024.arabicnlp-1.14.pdf","source":null,"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 Second Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671397.pdf","grobid_xml":"https://content.openalex.org/works/W4402671397.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4249048193","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-trained":[0],"Language":[1],"Models":[2],"(PLMs)":[3],"are":[4,40],"integral":[5],"to":[6,73,113],"many":[7],"modern":[8,44],"natural":[9],"language":[10],"processing":[11],"(NLP)":[12],"systems.Although":[13],"multilingual":[14],"models":[15,105],"cover":[16],"a":[17,32,79,97,124],"wide":[18],"range":[19],"of":[20,34,93,99,126],"languages,":[21],"they":[22],"often":[23],"grapple":[24],"with":[25],"challenges":[26],"like":[27],"high":[28],"inference":[29],"costs":[30],"and":[31,77,110,116],"lack":[33],"diverse":[35],"non-English":[36],"training":[37,133],"data.Arabic-specific":[38],"PLMs":[39],"trained":[41,88],"predominantly":[42],"on":[43,51,123],"standard":[45],"Arabic,":[46],"which":[47,95],"compromises":[48],"their":[49],"performance":[50,122],"regional":[52],"dialects.To":[53],"tackle":[54],"this,":[55],"we":[56],"construct":[57],"an":[58],"Arabic":[59,127],"dialectal":[60],"corpus":[61,72],"comprising":[62],"3.4M":[63],"sentences":[64],"gathered":[65],"from":[66,82],"social":[67],"media":[68],"platforms.We":[69],"utilize":[70],"this":[71],"expand":[74],"the":[75,100,131],"vocabulary":[76],"retrain":[78],"BERT-based":[80],"model":[81,86],"scratch.Named":[83],"AlcLaM,":[84],"our":[85],"was":[87],"using":[89],"only":[90],"13":[91],"GB":[92],"text,":[94],"represents":[96],"fraction":[98],"data":[101],"used":[102],"by":[103],"existing":[104],"such":[106],"as":[107],"CAMeL,":[108],"MARBERT,":[109],"ArBERT,":[111],"compared":[112],"7.8%,":[114],"10.2%,":[115],"21.3%,":[117],"respectively.Remarkably,":[118],"AlcLaM":[119],"demonstrates":[120],"superior":[121],"variety":[125],"NLP":[128],"tasks":[129],"despite":[130],"limited":[132],"data.AlcLaM":[134],"is":[135],"available":[136],"at:":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
