{"id":"https://openalex.org/W4385572949","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.49","title":"On The Arabic Dialects\u2019 Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets","display_name":"On The Arabic Dialects\u2019 Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572949","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.49"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.49","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.49","pdf_url":"https://aclanthology.org/2022.wanlp-1.49.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-1.49.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Salma Jamal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Salma Jamal","raw_affiliation_strings":["School of Information Technology and Computer Science, Nile University Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology and Computer Science, Nile University Giza, Egypt","institution_ids":["https://openalex.org/I57629906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052115677","display_name":"Aly M. Kassem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aly M .Kassem","raw_affiliation_strings":["School of Computer Science University of Windsor, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Windsor, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Omar Mohamed","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84058292","display_name":"Helwan University","ror":"https://ror.org/00h55v928","country_code":"EG","type":"education","lineage":["https://openalex.org/I84058292"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Omar Mohamed","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence Helwan University Helwan, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence Helwan University Helwan, Egypt","institution_ids":["https://openalex.org/I84058292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103547026","display_name":"Ali Ashraf","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84058292","display_name":"Helwan University","ror":"https://ror.org/00h55v928","country_code":"EG","type":"education","lineage":["https://openalex.org/I84058292"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Ashraf","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence Helwan University Helwan, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence Helwan University Helwan, Egypt","institution_ids":["https://openalex.org/I84058292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43089399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"458","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5073000192642212,"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":0.5073000192642212,"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":0.10719999670982361,"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":0.10279999673366547,"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/arabic-dialect-identification","display_name":"Arabic dialect identification","score":0.9739999771118164},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8560000061988831},{"id":"https://openalex.org/keywords/weighted-cross-entropy-loss","display_name":"weighted cross-entropy loss","score":0.7689999938011169},{"id":"https://openalex.org/keywords/hybrid-loss-function","display_name":"hybrid loss function","score":0.6779999732971191},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7255762815475464},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6917576789855957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572331786155701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6550774574279785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957934260368347},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5950026512145996},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5571467876434326},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4947187602519989},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4151137173175812},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37597787380218506},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08193311095237732},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2022.wanlp-1.49","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.49","pdf_url":"https://aclanthology.org/2022.wanlp-1.49.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"},{"id":"pmh:oai:figshare.com:article/26941429","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/On_The_Arabic_Dialects_Identification_Overcoming_Challenges_of_Geographical_Similarities_Between_Arabic_dialects_and_Imbalanced_Datasets/26941429","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wanlp-1.49","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.49","pdf_url":"https://aclanthology.org/2022.wanlp-1.49.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":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320330223","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572949.pdf","grobid_xml":"https://content.openalex.org/works/W4385572949.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2109704865","https://openalex.org/W2896457183","https://openalex.org/W2948902769","https://openalex.org/W2970814728","https://openalex.org/W3119566336","https://openalex.org/W3119652442","https://openalex.org/W3119989085","https://openalex.org/W3120373775","https://openalex.org/W3135678629","https://openalex.org/W3135784975","https://openalex.org/W3154301048","https://openalex.org/W3155312056","https://openalex.org/W3176169354","https://openalex.org/W4297663785","https://openalex.org/W4385573366","https://openalex.org/W4394657514"],"related_works":["https://openalex.org/W4385573366","https://openalex.org/W3120373775","https://openalex.org/W3135784975","https://openalex.org/W3119566336","https://openalex.org/W4389518436","https://openalex.org/W4402671457","https://openalex.org/W4385573495","https://openalex.org/W4394657514","https://openalex.org/W4389518352","https://openalex.org/W4385573141"],"abstract_inverted_index":{"Arabic":[0,34],"is":[1],"one":[2],"of":[3,12,31,55],"the":[4,32,51,57,62,75],"world's":[5],"richest":[6],"languages,":[7],"with":[8,44],"a":[9,22,80],"diverse":[10],"range":[11],"dialects":[13],"based":[14],"on":[15],"geographical":[16],"origin.In":[17],"this":[18],"paper,":[19],"we":[20,60,78],"present":[21],"solution":[23],"to":[24],"tackle":[25],"subtask":[26],"1":[27],"(Country-level":[28],"dialect":[29],"identification)":[30],"Nuanced":[33],"Dialect":[35],"Identification":[36],"(NADI)":[37],"shared":[38],"task":[39],"2022":[40],"achieving":[41],"third":[42],"place":[43],"an":[45],"average":[46],"macro":[47],"F1":[48,107],"score":[49],"between":[50],"two":[52],"test":[53,95],"sets":[54,96],"26.44%.In":[56],"preprocessing":[58],"stage,":[59],"removed":[61],"most":[63],"common":[64],"frequent":[65],"terms":[66],"from":[67],"all":[68,71],"sentences":[69],"across":[70],"dialects,":[72],"and":[73,91,98,104],"in":[74],"modeling":[76],"step,":[77],"employed":[79],"hybrid":[81],"loss":[82,90],"function":[83],"approach":[84],"that":[85],"includes":[86],"Weighted":[87],"cross":[88],"entropy":[89],"Vector":[92],"Scaling(VS)":[93],"Loss.On":[94],"A":[97],"B,":[99],"our":[100],"model":[101],"achieved":[102],"35.68%":[103],"17.192%":[105],"Macro":[106],"scores,":[108],"respectively.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}
