{"id":"https://openalex.org/W2970578875","doi":"https://doi.org/10.18653/v1/w19-4624","title":"Simple But Not Na\u00efve: Fine-Grained Arabic Dialect Identification Using Only N-Grams","display_name":"Simple But Not Na\u00efve: Fine-Grained Arabic Dialect Identification Using Only N-Grams","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970578875","doi":"https://doi.org/10.18653/v1/w19-4624","mag":"2970578875"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4624","pdf_url":"https://www.aclweb.org/anthology/W19-4624.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4624.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025251325","display_name":"Sohaila Eltanbouly","orcid":"https://orcid.org/0000-0002-4917-5851"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Sohaila Eltanbouly","raw_affiliation_strings":["Qatar University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051668357","display_name":"May Bashendy","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"May Bashendy","raw_affiliation_strings":["Qatar University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032141720","display_name":"Tamer Elsayed","orcid":"https://orcid.org/0000-0001-5786-4668"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Tamer Elsayed","raw_affiliation_strings":["Qatar University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032141720"],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58108916,"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":"214","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9993000030517578,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/computer-science","display_name":"Computer science","score":0.7803195714950562},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7260808944702148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7233361601829529},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7196996212005615},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7103605270385742},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7033037543296814},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6831380128860474},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.666304886341095},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6628429293632507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6352027654647827},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5537188053131104},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.45790600776672363},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4407362937927246},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2557315528392792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1268075406551361},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.0847528874874115},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.059133559465408325},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05249911546707153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803195714950562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7260808944702148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7233361601829529},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7196996212005615},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7103605270385742},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7033037543296814},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6831380128860474},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.666304886341095},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6628429293632507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352027654647827},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5537188053131104},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.45790600776672363},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4407362937927246},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2557315528392792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1268075406551361},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0847528874874115},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.059133559465408325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05249911546707153},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w19-4624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4624","pdf_url":"https://www.aclweb.org/anthology/W19-4624.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/60891","is_oa":true,"landing_page_url":"http://hdl.handle.net/10576/60891","pdf_url":"http://qspace.qu.edu.qa/bitstream/10576/60891/1/W19-4624.pdf","source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4624","pdf_url":"https://www.aclweb.org/anthology/W19-4624.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970578875.pdf","grobid_xml":"https://content.openalex.org/works/W2970578875.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1577352519","https://openalex.org/W2132474591","https://openalex.org/W2251433042","https://openalex.org/W2400103538","https://openalex.org/W2806962830","https://openalex.org/W2812315852","https://openalex.org/W2970513828","https://openalex.org/W3151357476"],"related_works":["https://openalex.org/W4392318734","https://openalex.org/W2620283452","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/W4403231732","https://openalex.org/W4299493485"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,15,31,51,90,107],"participation":[4],"of":[5,17,68,109,119],"Qatar":[6],"University":[7],"team":[8],"in":[9,28,66],"MADAR":[10],"shared":[11],"task,":[12],"which":[13],"addresses":[14],"problem":[16],"sentence-level":[18],"fine-grained":[19],"Arabic":[20,26,35],"Dialect":[21,36],"Identification":[22,37],"over":[23],"25":[24],"different":[25,44],"dialects":[27,45],"addition":[29],"to":[30,60],"Modern":[32],"Standard":[33],"Arabic.":[34],"is":[38],"not":[39],"a":[40,62,101,110],"trivial":[41],"task":[42],"since":[43],"share":[46],"some":[47,56],"features,":[48,82],"e.g.,":[49],"utilizing":[50],"same":[52],"character":[53,79],"set":[54],"and":[55,71,78,83],"vocabularies.":[57],"We":[58],"opted":[59],"adopt":[61],"very":[63],"simple":[64,91],"approach":[65,92],"terms":[67],"extracted":[69],"features":[70],"classification":[72],"models;":[73],"we":[74],"only":[75],"utilize":[76],"word":[77],"ngrams":[80],"as":[81,87],"Nave":[84],"Bayes":[85],"models":[86],"classifiers.":[88],"Surprisingly,":[89],"achieved":[93],"non-nave":[94],"performance.":[95],"The":[96],"official":[97],"results,":[98],"reported":[99],"on":[100],"held-out":[102],"testing":[103],"set,":[104],"show":[105],"that":[106],"dialect":[108],"given":[111],"sentence":[112],"can":[113],"be":[114],"identified":[115],"at":[116],"an":[117],"accuracy":[118],"64.58%":[120],"by":[121],"our":[122],"best":[123],"submitted":[124],"run.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
