{"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","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":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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K15-1005.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073237528","display_name":"Mohamed Al-Badrashiny","orcid":null},"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},"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"},"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":null,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.996399998664856,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9918000102043152,"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/security-token","display_name":"Security token","score":0.8337517976760864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7725121974945068},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7595638036727905},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7328232526779175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7105696201324463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5991844534873962},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.490667462348938},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4635784924030304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43746182322502136},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4180499315261841},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.35803890228271484},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14355921745300293}],"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","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":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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi: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":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 Nineteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"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/W2620283452","https://openalex.org/W4392318734","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W2801712537","https://openalex.org/W4396221470","https://openalex.org/W587642979","https://openalex.org/W2894059694","https://openalex.org/W4299493485","https://openalex.org/W589191641"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,19,120],"present":[4],"a":[5,27,60,77,83,98,117,169],"hybrid":[6],"approach":[7],"for":[8,127,161],"performing":[9],"token":[10,25,55,165],"and":[11,44,81,82,143,187],"sentence":[12,29,48,94,189],"levels":[13],"Dialect":[14],"Identification":[15],"in":[16,26,90],"Arabic.":[17],"Specifically":[18],"try":[20],"to":[21,31,86,155,179,198],"identify":[22],"whether":[23,45],"each":[24,88,128,149,162],"given":[28],"belongs":[30],"Modern":[32],"Standard":[33],"Arabic":[34,38],"(MSA),":[35],"Egyptian":[36],"Dialectal":[37],"(EDA)":[39],"or":[40,52],"some":[41],"other":[42],"class":[43,141,160],"the":[46,91,114,122,140,144,151,158,173,183,188,202,206],"whole":[47],"is":[49],"mostly":[50],"EDA":[51],"MSA.":[53],"The":[54,93,164],"level":[56,95,166,190],"component":[57,96,167,191],"relies":[58,103],"on":[59,104],"Conditional":[61],"Random":[62],"Field":[63],"(CRF)":[64],"classifier":[65,99,137],"that":[66,102,109,138],"uses":[67,97,139],"decisions":[68],"from":[69],"several":[70],"underlying":[71,107,153],"components":[72],"such":[73],"as":[74],"language":[75],"models,":[76],"named":[78],"entity":[79],"recognizer":[80],"morphological":[84],"analyzer":[85],"label":[87],"word":[89],"sentence.":[92,163],"ensemble":[100],"system":[101],"two":[105,131,152],"independent":[106],"classifiers":[108,154],"model":[110],"different":[111],"aspects":[112],"of":[113,125,129,150,172,176,182,185,195,205],"language.":[115],"Using":[116],"featureselection":[118],"heuristic,":[119],"select":[121],"best":[123,203],"set":[124],"features":[126],"these":[130],"classifiers.":[132],"We":[133],"then":[134],"train":[135],"another":[136],"labels":[142],"confidence":[145],"scores":[146],"generated":[147],"by":[148,201],"decide":[156],"upon":[157],"final":[159],"yields":[168,192],"new":[170],"state":[171,181,204],"art":[174,184,207],"F-score":[175],"90.6%":[177],"(compared":[178,197],"previous":[180],"86.8%)":[186],"an":[193],"accuracy":[194],"90.8%":[196],"86.6%":[199],"obtained":[200],"system).":[208]},"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":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}