{"id":"https://openalex.org/W2970354905","doi":"https://doi.org/10.18653/v1/w19-4603","title":"POS Tagging for Improving Code-Switching Identification in Arabic","display_name":"POS Tagging for Improving Code-Switching Identification in Arabic","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970354905","doi":"https://doi.org/10.18653/v1/w19-4603","mag":"2970354905"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4603","pdf_url":"https://www.aclweb.org/anthology/W19-4603.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/W19-4603.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Mohammed Attia","raw_affiliation_strings":["Google LLC, New York City, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, New York City, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Younes Samih","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091764449","display_name":"Ali Elkahky","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":"Ali Elkahky","raw_affiliation_strings":["Google LLC, New York City, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, New York City, 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/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"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/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Darwish","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU Research Complex, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075586667"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.111,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96114827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10265","display_name":"Multilingual Education and Policy","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T10265","display_name":"Multilingual Education and Policy","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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/T12031","display_name":"Speech and dialogue systems","score":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.820892870426178},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.8128483295440674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7102612257003784},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6274662613868713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5982571840286255},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5830612182617188},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5714097619056702},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5711976885795593},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5663394331932068},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5268957614898682},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4892392158508301},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4177170395851135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4063272476196289},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3449831008911133},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2672869563102722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820892870426178},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.8128483295440674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7102612257003784},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6274662613868713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982571840286255},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5830612182617188},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5714097619056702},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5711976885795593},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5663394331932068},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5268957614898682},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4892392158508301},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4177170395851135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4063272476196289},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3449831008911133},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2672869563102722},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4603","pdf_url":"https://www.aclweb.org/anthology/W19-4603.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"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4603","pdf_url":"https://www.aclweb.org/anthology/W19-4603.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970354905.pdf","grobid_xml":"https://content.openalex.org/works/W2970354905.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W305981506","https://openalex.org/W371426616","https://openalex.org/W620443118","https://openalex.org/W941093546","https://openalex.org/W1481490983","https://openalex.org/W1496496407","https://openalex.org/W1521568674","https://openalex.org/W1614298861","https://openalex.org/W1728883788","https://openalex.org/W1783519389","https://openalex.org/W1904365287","https://openalex.org/W1940872118","https://openalex.org/W1982789857","https://openalex.org/W2002019621","https://openalex.org/W2005010291","https://openalex.org/W2013489815","https://openalex.org/W2013583388","https://openalex.org/W2014962660","https://openalex.org/W2032715518","https://openalex.org/W2048512899","https://openalex.org/W2049907881","https://openalex.org/W2064675550","https://openalex.org/W2094655846","https://openalex.org/W2098355803","https://openalex.org/W2121227244","https://openalex.org/W2126784811","https://openalex.org/W2131774270","https://openalex.org/W2135064956","https://openalex.org/W2145867197","https://openalex.org/W2148906861","https://openalex.org/W2156876426","https://openalex.org/W2158899491","https://openalex.org/W2160848811","https://openalex.org/W2168708086","https://openalex.org/W2188330943","https://openalex.org/W2250854801","https://openalex.org/W2250967669","https://openalex.org/W2251149908","https://openalex.org/W2251699420","https://openalex.org/W2252095989","https://openalex.org/W2252113950","https://openalex.org/W2296283641","https://openalex.org/W2338893019","https://openalex.org/W2471774947","https://openalex.org/W2493916176","https://openalex.org/W2497649134","https://openalex.org/W2528420710","https://openalex.org/W2530571334","https://openalex.org/W2550821151","https://openalex.org/W2557418006","https://openalex.org/W2740286348","https://openalex.org/W2788190679","https://openalex.org/W2952230511","https://openalex.org/W2962902328","https://openalex.org/W2963293280","https://openalex.org/W2963625095","https://openalex.org/W2963682821","https://openalex.org/W2963940534","https://openalex.org/W3098911752","https://openalex.org/W4237155282","https://openalex.org/W4255065514","https://openalex.org/W4388154939","https://openalex.org/W4393327169","https://openalex.org/W4403817633"],"related_works":["https://openalex.org/W2620283452","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W2801712537","https://openalex.org/W4396221470","https://openalex.org/W4310665626","https://openalex.org/W587642979","https://openalex.org/W226586525","https://openalex.org/W2894059694","https://openalex.org/W4403231732"],"abstract_inverted_index":{"When":[0],"speakers":[1],"code-switch":[2],"between":[3,46],"their":[4],"native":[5],"language":[6,10,12,26,130],"and":[7,21,51,96],"a":[8,16,74],"second":[9],"or":[11],"variant,":[13],"they":[14],"follow":[15],"syntactic":[17],"pattern":[18,41],"where":[19,119],"words":[20,121,136],"phrases":[22],"from":[23,127,138],"the":[24,30,36,59,65,87,93,99,109,128,132,139],"embedded":[25],"are":[27],"inserted":[28],"into":[29],"matrix":[31],"language.":[32,141],"This":[33],"paper":[34],"explores":[35],"possibility":[37],"of":[38,61,111,134],"utilizing":[39],"this":[40],"in":[42,68,106],"improving":[43],"code-switching":[44,70],"identification":[45],"Modern":[47],"Standard":[48],"Arabic":[49,53],"(MSA)":[50],"Egyptian":[52],"(EA).":[54],"We":[55,72,102],"try":[56],"to":[57,123],"answer":[58],"question":[60],"how":[62],"strong":[63],"is":[64,114],"POS":[66,83,117],"signal":[67],"word-level":[69],"identification.":[71],"build":[73],"deep":[75],"learning":[76],"model":[77],"enriched":[78],"with":[79],"linguistic":[80],"features":[81],"(including":[82],"tags)":[84],"that":[85,105],"outperforms":[86],"state-of-the-art":[88],"results":[89],"by":[90,116],"1.9%":[91],"on":[92,98],"development":[94],"set":[95],"1.0%":[97],"test":[100],"set.":[101],"also":[103],"show":[104],"intrasentential":[107],"code-switching,":[108],"selection":[110],"lexical":[112],"items":[113],"constrained":[115],"categories,":[118],"function":[120],"tend":[122],"come":[124,137],"more":[125],"often":[126],"dialectal":[129],"while":[131],"majority":[133],"content":[135],"standard":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}