{"id":"https://openalex.org/W2252222397","doi":"https://doi.org/10.18653/v1/k15-1005","title":"AIDA2: A Hybrid Approach for Token and Sentence Level Dialect Identification in Arabic","display_name":"AIDA2: A Hybrid Approach for Token and Sentence Level Dialect Identification in Arabic","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252222397","doi":"https://doi.org/10.18653/v1/k15-1005","mag":"2252222397"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k15-1005","doi":"https://doi.org/10.18653/v1/k15-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k15-1005","pdf_url":"https://www.aclweb.org/anthology/K15-1005.pdf","source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/K15-1005.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073237528","display_name":"Mohamed A. S. A. A. Al-Badrashiny","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Al-Badrashiny","raw_affiliation_strings":["Department of Computer Science, The George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077304103","display_name":"Heba Elfardy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heba Elfardy","raw_affiliation_strings":["Department of Computer Science, Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436","observed_orcids":["https://orcid.org/0000-0002-7696-1436"]},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Diab","raw_affiliation_strings":["Department of Computer Science, The George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0044,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93359465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9419000148773193,"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":0.9419000148773193,"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":0.017500000074505806,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.008299999870359898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dialect-identification","display_name":"dialect identification","score":0.871999979019165},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.8849999904632568},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.8700000047683716},{"id":"https://openalex.org/keywords/sentence-level-classification","display_name":"sentence-level classification","score":0.9990000128746033},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.7400000095367432},{"id":"https://openalex.org/keywords/ensemble-classifiers","display_name":"ensemble classifiers","score":0.8790000081062317},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.8759999871253967},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.7860000133514404},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.9129999876022339},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.75}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8337517976760864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725121974945068},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7595638036727905},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7328232526779175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7105696201324463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5991844534873962},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.490667462348938},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4635784924030304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43746182322502136},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4180499315261841},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.35803890228271484},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14355921745300293},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":1,"locations":[{"id":"doi:10.18653/v1/k15-1005","doi":"https://doi.org/10.18653/v1/k15-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k15-1005","pdf_url":"https://www.aclweb.org/anthology/K15-1005.pdf","source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k15-1005","doi":"https://doi.org/10.18653/v1/k15-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k15-1005","pdf_url":"https://www.aclweb.org/anthology/K15-1005.pdf","source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252222397.pdf","grobid_xml":"https://content.openalex.org/works/W2252222397.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W131663347","https://openalex.org/W1728883788","https://openalex.org/W2109704865","https://openalex.org/W2109926133","https://openalex.org/W2133990480","https://openalex.org/W2135161317","https://openalex.org/W2136534344","https://openalex.org/W2137498753","https://openalex.org/W2142384583","https://openalex.org/W2156515921","https://openalex.org/W2168677000","https://openalex.org/W2250278916","https://openalex.org/W2250816155","https://openalex.org/W2250932402","https://openalex.org/W2251149908","https://openalex.org/W2251986002","https://openalex.org/W2252176750","https://openalex.org/W4237155282"],"related_works":["https://openalex.org/W2251986002","https://openalex.org/W4318567029","https://openalex.org/W2900745228","https://openalex.org/W7217839369","https://openalex.org/W4224289022","https://openalex.org/W6973633513","https://openalex.org/W7139082043","https://openalex.org/W4389518330","https://openalex.org/W2971355343","https://openalex.org/W2115295410"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,18,116],"present":[4],"a":[5,26,58,75,81,95,113,163],"hybrid":[6],"approach":[7],"for":[8,123,156],"performing":[9],"token":[10,24,53,159],"and":[11,43,79,80,138,181],"sentence":[12,28,47,91,183],"levels":[13],"Dialect":[14],"Identification":[15],"in":[16,25,88],"Arabic.Specifically":[17],"try":[19],"to":[20,30,84,150,173,192],"identify":[21],"whether":[22,44],"each":[23,86,124,144,157],"given":[27],"belongs":[29],"Modern":[31],"Standard":[32],"Arabic":[33,37],"(MSA),":[34],"Egyptian":[35],"Dialectal":[36],"(EDA)":[38],"or":[39,51],"some":[40],"other":[41],"class":[42,136,155],"the":[45,89,111,118,135,139,146,153,167,177,182,196,200],"whole":[46],"is":[48],"mostly":[49],"EDA":[50],"MSA.The":[52],"level":[54,92,160,184],"component":[55,93,161,185],"relies":[56,100],"on":[57,101],"Conditional":[59],"Random":[60],"Field":[61],"(CRF)":[62],"classifier":[63,96,132],"that":[64,99,106,133],"uses":[65,94,134],"decisions":[66],"from":[67],"several":[68],"underlying":[69,104,148],"components":[70],"such":[71],"as":[72],"language":[73],"models,":[74],"named":[76],"entity":[77],"recognizer":[78],"morphological":[82],"analyzer":[83],"label":[85],"word":[87],"sentence.The":[90,158],"ensemble":[97],"system":[98],"two":[102,127,147],"independent":[103],"classifiers":[105,149],"model":[107],"different":[108],"aspects":[109],"of":[110,121,125,145,166,170,176,179,189,199],"language.Using":[112],"featureselection":[114],"heuristic,":[115],"select":[117],"best":[119,197],"set":[120],"features":[122],"these":[126],"classifiers.We":[128],"then":[129],"train":[130],"another":[131],"labels":[137],"confidence":[140],"scores":[141],"generated":[142],"by":[143,195],"decide":[151],"upon":[152],"final":[154],"yields":[162,186],"new":[164],"state":[165,175,198],"art":[168,178,201],"F-score":[169],"90.6%":[171],"(compared":[172,191],"previous":[174],"86.8%)":[180],"an":[187],"accuracy":[188],"90.8%":[190],"86.6%":[193],"obtained":[194],"system).":[202]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2016,"cited_by_count":8}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}