{"id":"https://openalex.org/W3016397003","doi":"https://doi.org/10.1017/s1351324920000078","title":"Effective multi-dialectal arabic POS tagging","display_name":"Effective multi-dialectal arabic POS tagging","publication_year":2020,"publication_date":"2020-04-14","ids":{"openalex":"https://openalex.org/W3016397003","doi":"https://doi.org/10.1017/s1351324920000078","mag":"3016397003"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324920000078","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000078","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Darwish","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075586667","display_name":"Mohammed Attia","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Attia","raw_affiliation_strings":["Google Inc New York, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc New York, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086381528","display_name":"Younes Samih","orcid":"https://orcid.org/0000-0002-0485-7920"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Younes Samih","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-4160-8181","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103372090","display_name":"Llu\u0131\u0301s M\u00e0rquez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Llu\u00eds M\u00e0rquez","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033221342","display_name":"Mohamed Eldesouki","orcid":"https://orcid.org/0009-0009-6662-5883"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohamed Eldesouki","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004268590","display_name":"Laura Kallmeyer","orcid":"https://orcid.org/0000-0001-9691-5990"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Laura Kallmeyer","raw_affiliation_strings":["Computational Linguistics Department, Heinrich-Heine-University D\u00fcsseldorf, 40204D\u00fcsseldorf, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics Department, Heinrich-Heine-University D\u00fcsseldorf, 40204D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047182137"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":0.9512,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80683844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"6","first_page":"677","last_page":"690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9965999722480774,"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/crfs","display_name":"CRFS","score":0.877641499042511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8652871251106262},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6203523278236389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147637963294983},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5934723615646362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5427641272544861},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5364262461662292},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5264694690704346},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5058298110961914},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5041102170944214},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44108375906944275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32870179414749146},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10793066024780273}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.877641499042511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652871251106262},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6203523278236389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147637963294983},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5934723615646362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5427641272544861},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5364262461662292},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5264694690704346},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5058298110961914},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5041102170944214},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44108375906944275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32870179414749146},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10793066024780273},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324920000078","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000078","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W78842653","https://openalex.org/W371426616","https://openalex.org/W1904365287","https://openalex.org/W1940872118","https://openalex.org/W2043693083","https://openalex.org/W2064675550","https://openalex.org/W2109704865","https://openalex.org/W2121227244","https://openalex.org/W2123777430","https://openalex.org/W2126784811","https://openalex.org/W2131774270","https://openalex.org/W2138738738","https://openalex.org/W2147880316","https://openalex.org/W2157765050","https://openalex.org/W2158049734","https://openalex.org/W2158899491","https://openalex.org/W2250278916","https://openalex.org/W2250414785","https://openalex.org/W2250732891","https://openalex.org/W2250783208","https://openalex.org/W2250816155","https://openalex.org/W2251699420","https://openalex.org/W2251986002","https://openalex.org/W2295824561","https://openalex.org/W2296283641","https://openalex.org/W2471147443","https://openalex.org/W2740130688","https://openalex.org/W2740645003","https://openalex.org/W2740918723","https://openalex.org/W2788190679","https://openalex.org/W2952230511","https://openalex.org/W2962902328","https://openalex.org/W2963625095","https://openalex.org/W2963682821","https://openalex.org/W2963940534","https://openalex.org/W6640362995","https://openalex.org/W6678277124","https://openalex.org/W6682082992","https://openalex.org/W6683161899","https://openalex.org/W6683738474","https://openalex.org/W6690971519","https://openalex.org/W6691129875","https://openalex.org/W6691363017","https://openalex.org/W6742068184","https://openalex.org/W6742092604","https://openalex.org/W6748101063"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2511246383","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2184553228"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"work":[2],"introduces":[3],"robust":[4,91],"multi-dialectal":[5,96],"part":[6],"of":[7,16,59,74,107,129,135],"speech":[8],"tagging":[9,34],"trained":[10],"on":[11],"an":[12],"annotated":[13],"data":[14,133],"set":[15,134],"Arabic":[17],"tweets":[18,97,137],"in":[19,51],"four":[20],"major":[21],"dialect":[22,114],"groups:":[23],"Egyptian,":[24],"Levantine,":[25],"Gulf,":[26],"and":[27,48,61,85,98,119],"Maghrebi.":[28],"We":[29,69,102,121],"implement":[30],"two":[31],"different":[32],"sequence":[33],"approaches.":[35],"The":[36],"first":[37],"uses":[38],"conditional":[39],"random":[40],"fields":[41],"(CRFs),":[42],"while":[43],"the":[44,123],"second":[45],"combines":[46],"word-":[47],"character-based":[49],"representations":[50],"a":[52,65,72,104,126,132],"deep":[53],"neural":[54],"network":[55],"with":[56,64,112],"stacked":[57],"layers":[58],"convolutional":[60],"recurrent":[62],"networks":[63],"CRF":[66],"output":[67],"layer.":[68],"successfully":[70],"exploit":[71],"variety":[73],"features":[75],"that":[76,94],"help":[77],"generalize":[78],"our":[79],"models,":[80],"such":[81],"as":[82],"Brown":[83],"clusters":[84],"stem":[86],"templates.":[87],"Also,":[88],"we":[89],"develop":[90],"joint":[92],"models":[93],"tag":[95],"outperform":[99],"uni-dialectal":[100],"taggers.":[101],"achieve":[103],"combined":[105],"accuracy":[106],"92.4%":[108],"across":[109],"all":[110],"dialects,":[111],"per":[113,138],"results":[115,124],"ranging":[116],"between":[117],"90.2%":[118],"95.4%.":[120],"obtained":[122],"using":[125],"train/dev/test":[127],"split":[128],"70/10/20":[130],"for":[131],"350":[136],"dialect.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
