{"id":"https://openalex.org/W7140084480","doi":"https://doi.org/10.18653/v1/2026.vardial-1.21","title":"Syllable Structures Across Arabic Varieties","display_name":"Syllable Structures Across Arabic Varieties","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140084480","doi":"https://doi.org/10.18653/v1/2026.vardial-1.21"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.vardial-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.21","pdf_url":"https://aclanthology.org/2026.vardial-1.21.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.vardial-1.21.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109663423","display_name":"Abdelrahim Qaddoumi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahim Qaddoumi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050460997","display_name":"Jordan Kodner","orcid":"https://orcid.org/0000-0001-8632-9859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordan Kodner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019390269","display_name":"Salam Khalifa","orcid":"https://orcid.org/0000-0003-0049-3637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salam Khalifa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014677796","display_name":"Ellen Broselow","orcid":"https://orcid.org/0000-0001-8097-8399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellen Broselow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130339192","display_name":"Owen Rambow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Owen Rambow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37396997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.2126999944448471,"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"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.2126999944448471,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.20180000364780426,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.09390000253915787,"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/syllable","display_name":"Syllable","score":0.753600001335144},{"id":"https://openalex.org/keywords/syllabification","display_name":"Syllabification","score":0.7279000282287598},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5852000117301941},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.42750000953674316},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.38530001044273376},{"id":"https://openalex.org/keywords/obstruent","display_name":"Obstruent","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.753600001335144},{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.7279000282287598},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46939998865127563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4618000090122223},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C3156200","wikidata":"https://www.wikidata.org/wiki/Q1148563","display_name":"Obstruent","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33739998936653137},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2778575526","wikidata":"https://www.wikidata.org/wiki/Q2631145","display_name":"Varieties of English","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.vardial-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.21","pdf_url":"https://aclanthology.org/2026.vardial-1.21.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.vardial-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.21","pdf_url":"https://aclanthology.org/2026.vardial-1.21.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331904","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140084480.pdf","grobid_xml":"https://content.openalex.org/works/W7140084480.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"compares":[2],"the":[3,28,68,72,88],"syllable":[4,21],"structures":[5],"of":[6],"nine":[7,135],"Arabic":[8,110],"varieties":[9,53,117,136],"from":[10,76,92],"Wiktionary,":[11],"using":[12,98],"a":[13,119],"computational":[14],"syllabifier.It":[15],"further":[16],"investigates":[17],"methods":[18],"for":[19],"learning":[20,47,58],"boundaries":[22],"in":[23,27],"unsyllabified":[24],"words":[25],"transcribed":[26],"International":[29],"Phonetic":[30],"Alphabet":[31],"(IPA).The":[32],"syllabification":[33],"algorithm":[34],"is":[35,137],"evaluated":[36],"under":[37],"three":[38,102],"conditions:":[39],"(i)":[40],"Default,":[41],"employing":[42],"fixed":[43],"rules;":[44],"(ii)":[45],"Joint,":[46],"onsets":[48,59],"and":[49,55,60,107,115,122,126],"codas":[50,61],"across":[51],"all":[52,134],"collectively;":[54],"(iii)":[56],"Per-variety,":[57],"specific":[62],"to":[63,78,84,94],"each":[64],"variety.Results":[65],"indicate":[66],"that":[67],"default":[69],"configuration":[70],"yields":[71],"highest":[73],"accuracy,":[74,86],"ranging":[75],"97.05%":[77],"100%.The":[79],"per-variety":[80],"approach":[81,90],"achieves":[82],"90.64%":[83],"100%":[85],"while":[87],"joint":[89],"ranges":[91],"84.63%":[93],"94.74%.A":[95],"cross-variety":[96],"analysis":[97],"Jensen-Shannon":[99],"divergence":[100],"reveals":[101],"principal":[103],"groupings:":[104],"Egyptian,":[105],"Hejazi,":[106],"Modern":[108],"Standard":[109],"are":[111],"closely":[112],"related;":[113],"Levantine":[114],"Gulf":[116],"constitute":[118],"second":[120],"cluster;":[121],"Juba":[123],"Arabic,":[124],"Maltese,":[125],"Moroccan":[127],"emerge":[128],"as":[129],"outliers.A":[130],"cleaned":[131],"dataset":[132],"encompassing":[133],"also":[138],"provided.":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}