{"id":"https://openalex.org/W2805974756","doi":"https://doi.org/10.63317/4i96mxb3ymx8","title":"Shami: A Corpus of Levantine Arabic Dialects","display_name":"Shami: A Corpus of Levantine Arabic Dialects","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2805974756","doi":"https://doi.org/10.63317/4i96mxb3ymx8","mag":"2805974756"},"language":"en","primary_location":{"id":"doi:10.63317/4i96mxb3ymx8","doi":"https://doi.org/10.63317/4i96mxb3ymx8","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4i96mxb3ymx8","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/820.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/820.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023712503","display_name":"Kathrein Abu Kwaik","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kathrein Abu Kwaik","raw_affiliation_strings":["University of Gothenburg, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012780017","display_name":"Motaz Saad","orcid":"https://orcid.org/0000-0002-1080-7276","observed_orcids":["https://orcid.org/0000-0002-1080-7276"]},"institutions":[{"id":"https://openalex.org/I181086730","display_name":"Islamic University of Gaza","ror":"https://ror.org/057ts1y80","country_code":"PS","type":"education","lineage":["https://openalex.org/I181086730"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Motaz Saad","raw_affiliation_strings":["The Islamic University of Gaza , Palestine","Islamic University of Gaza, Gaza, Palestinian Territory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Islamic University of Gaza , Palestine","institution_ids":["https://openalex.org/I181086730"]},{"raw_affiliation_string":"Islamic University of Gaza, Gaza, Palestinian Territory","institution_ids":["https://openalex.org/I181086730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020791896","display_name":"Stergios Chatzikyriakidis","orcid":"https://orcid.org/0000-0001-8016-9743","observed_orcids":["https://orcid.org/0000-0001-8016-9743","https://orcid.org/0009-0008-8482-2162"]},"institutions":[{"id":"https://openalex.org/I181086730","display_name":"Islamic University of Gaza","ror":"https://ror.org/057ts1y80","country_code":"PS","type":"education","lineage":["https://openalex.org/I181086730"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["PS","SE"],"is_corresponding":false,"raw_author_name":"Stergios Chatzikyriakidis","raw_affiliation_strings":["The Islamic University of Gaza , Palestine","University of Gothenburg, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Islamic University of Gaza , Palestine","institution_ids":["https://openalex.org/I181086730"]},{"raw_affiliation_string":"University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014291440","display_name":"Simon Dobnik","orcid":"https://orcid.org/0000-0002-4019-7966","observed_orcids":["https://orcid.org/0000-0002-4019-7966"]},"institutions":[{"id":"https://openalex.org/I181086730","display_name":"Islamic University of Gaza","ror":"https://ror.org/057ts1y80","country_code":"PS","type":"education","lineage":["https://openalex.org/I181086730"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["PS","SE"],"is_corresponding":false,"raw_author_name":"Simon Dobnik","raw_affiliation_strings":["The Islamic University of Gaza , Palestine","University of Gothenburg, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Islamic University of Gaza , Palestine","institution_ids":["https://openalex.org/I181086730"]},{"raw_affiliation_string":"University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6432,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.93230367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9887999892234802,"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":0.9887999892234802,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.0026000000070780516,"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/T12031","display_name":"Speech and dialogue systems","score":0.00139999995008111,"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/dialect-identification","display_name":"dialect identification","score":0.8579999804496765},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.8069999814033508},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.7400000095367432},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.625},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.8190000057220459},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763947606086731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7051861882209778},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.701974093914032},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6220376491546631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886639952659607},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5591917634010315},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5527146458625793},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.5055103302001953},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4910562038421631},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4351285398006439},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.42922306060791016},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4281467795372009},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42356932163238525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23209011554718018},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18327021598815918},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.11162859201431274},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09191003441810608},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/4i96mxb3ymx8","doi":"https://doi.org/10.63317/4i96mxb3ymx8","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4i96mxb3ymx8","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/820.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"mag:2805974756","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/L18-1576.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/4i96mxb3ymx8","doi":"https://doi.org/10.63317/4i96mxb3ymx8","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4i96mxb3ymx8","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/820.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805974756.pdf","grobid_xml":"https://content.openalex.org/works/W2805974756.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W137989762","https://openalex.org/W1010239220","https://openalex.org/W1533946607","https://openalex.org/W1747652674","https://openalex.org/W1983102112","https://openalex.org/W2101234009","https://openalex.org/W2103195385","https://openalex.org/W2109704865","https://openalex.org/W2117099982","https://openalex.org/W2117202778","https://openalex.org/W2123442489","https://openalex.org/W2147272182","https://openalex.org/W2160802179","https://openalex.org/W2168677000","https://openalex.org/W2250185284","https://openalex.org/W2250783208","https://openalex.org/W2251986002","https://openalex.org/W2394969460","https://openalex.org/W2406392101","https://openalex.org/W2786351641"],"related_works":["https://openalex.org/W7216829323","https://openalex.org/W3026166316","https://openalex.org/W6977809669","https://openalex.org/W3191380211","https://openalex.org/W2790423975","https://openalex.org/W2978948973","https://openalex.org/W4281250659","https://openalex.org/W2041246285","https://openalex.org/W7139082043","https://openalex.org/W6973633513"],"abstract_inverted_index":{"Modern":[0],"Standard":[1],"Arabic":[2],"(MSA)":[3],"is":[4,117,154],"the":[5,14,30,41,46,52,57,72,75,83,86,95,112,126,157,170,173,179,184],"official":[6],"language":[7],"used":[8],"in":[9,18,23,99,160,183],"education":[10],"and":[11,20,56,77,103,131,150,165,181],"media":[12],"across":[13],"Arab":[15],"world":[16],"both":[17],"writing":[19],"formal":[21],"speech.However,":[22],"daily":[24],"communication":[25],"several":[26],"dialects":[27,76,97],"depending":[28],"on":[29,51,147,172],"country,":[31],"region":[32],"as":[33,35,125],"well":[34],"other":[36,136],"social":[37,44],"factors,":[38],"are":[39,63,141],"used.With":[40],"emergence":[42],"of":[43,49,162],"media,":[45],"dialectal":[47],"amount":[48],"data":[50,69,93],"Internet":[53],"have":[54],"increased":[55],"NLP":[58,120],"tools":[59],"that":[60,115],"support":[61],"MSA":[62],"not":[64],"well-suited":[65],"to":[66,71,128,177],"process":[67],"this":[68,79,138],"due":[70],"difference":[73],"between":[74],"MSA.In":[78],"paper,":[80],"we":[81,168],"construct":[82],"Shami":[84],"corpus,":[85],"first":[87],"Levantine":[88],"Dialect":[89,123],"Corpus":[90],"(SDC)":[91],"covering":[92],"from":[94],"four":[96],"spoken":[98],"Palestine,":[100],"Jordan,":[101],"Lebanon":[102],"Syria.We":[104],"also":[105],"describe":[106],"rules":[107],"for":[108],"pre-processing":[109],"without":[110],"affecting":[111],"meaning":[113],"so":[114],"it":[116,133],"processable":[118],"by":[119],"tools.We":[121],"choose":[122],"Identification":[124,175],"task":[127,176],"evaluate":[129],"SDC":[130],"compare":[132],"with":[134],"two":[135],"corpora.In":[137],"respect,":[139],"experiments":[140],"conducted":[142],"using":[143],"different":[144],"parameters":[145],"based":[146],"n-gram":[148],"models":[149],"Naive":[151],"Bayes":[152],"classifiers.SDC":[153],"larger":[155],"than":[156],"existing":[158],"corpora":[159],"terms":[161],"size,":[163],"words":[164],"vocabularies.In":[166],"addition,":[167],"use":[169],"performance":[171],"Language":[174],"exemplify":[178],"similarities":[180],"differences":[182],"individual":[185],"dialects.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2018-06-13T00:00:00"}
