{"id":"https://openalex.org/W4391528993","doi":"https://doi.org/10.1109/cist56084.2023.10410009","title":"Challenges and Progress in Constructing Arabic Dialect Corpora and Linguistic tools: A Focus on Moroccan and Tunisian Dialects","display_name":"Challenges and Progress in Constructing Arabic Dialect Corpora and Linguistic tools: A Focus on Moroccan and Tunisian Dialects","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391528993","doi":"https://doi.org/10.1109/cist56084.2023.10410009"},"language":"en","primary_location":{"id":"doi:10.1109/cist56084.2023.10410009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist56084.2023.10410009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 7th IEEE Congress on Information Science and Technology (CiSt)","raw_type":"proceedings-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/A5009123662","display_name":"Ouafae Nahli","orcid":"https://orcid.org/0000-0003-3147-7082"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ouafae Nahli","raw_affiliation_strings":["Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","Via G. Moruzzi, 1, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Via G. Moruzzi, 1, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087448640","display_name":"Elisa Gugliotta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Gugliotta","raw_affiliation_strings":["Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","Via G. Moruzzi, 1, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Via G. Moruzzi, 1, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102613346","display_name":"Nadia Khlif","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nadia Khlif","raw_affiliation_strings":["Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","Via G. Moruzzi, 1, Pisa, Italy","Laboratoire des recherches informatiques university Mohammed First Oujda"],"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Via G. Moruzzi, 1, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Laboratoire des recherches informatiques university Mohammed First Oujda","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014129424","display_name":"Benotto Giulia","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Benotto Giulia","raw_affiliation_strings":["Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","Via G. Moruzzi, 1, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale, Consiglio Nazionale delle Ricerche; Via G. Moruzzi, 1,Pisa,Italy,56124","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Via G. Moruzzi, 1, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009123662"],"corresponding_institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210124522"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68026377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.945900022983551,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9455999732017517,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/focus","display_name":"Focus (optics)","score":0.7792726159095764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7296629548072815},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6414357423782349},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6364007592201233},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6031132936477661},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5303690433502197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45046138763427734},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.4210612177848816}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7792726159095764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296629548072815},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6414357423782349},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6364007592201233},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6031132936477661},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303690433502197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45046138763427734},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4210612177848816},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cist56084.2023.10410009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist56084.2023.10410009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 7th IEEE Congress on Information Science and Technology (CiSt)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1969719558","https://openalex.org/W2004586385","https://openalex.org/W2302501749","https://openalex.org/W2465804994","https://openalex.org/W2740432722","https://openalex.org/W2740645003","https://openalex.org/W2799399790","https://openalex.org/W2915357442","https://openalex.org/W3007095894","https://openalex.org/W3103339821","https://openalex.org/W3138381435","https://openalex.org/W4214870491","https://openalex.org/W4307922498","https://openalex.org/W4314932272","https://openalex.org/W4385573130","https://openalex.org/W6605374713","https://openalex.org/W6690971519","https://openalex.org/W6691525129","https://openalex.org/W6748101063","https://openalex.org/W6748806985","https://openalex.org/W6752194034","https://openalex.org/W6752253946","https://openalex.org/W6777988561","https://openalex.org/W6839581624","https://openalex.org/W6858148020"],"related_works":["https://openalex.org/W2352058714","https://openalex.org/W4249048193","https://openalex.org/W2357256365","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W2348502264","https://openalex.org/W2365486383","https://openalex.org/W2362059367","https://openalex.org/W2337443140","https://openalex.org/W2012531322"],"abstract_inverted_index":{"Given":[0],"the":[1,8,23,76,88],"lack":[2],"of":[3,10,22,90],"resources":[4,61],"for":[5,65],"Arabic":[6],"dialects,":[7],"construction":[9],"corpora,":[11],"lexical":[12,48],"resources,":[13],"and":[14,39,46,83],"tools":[15],"is":[16,25],"a":[17],"non-trivial":[18],"challenge.":[19],"The":[20],"focus":[21],"article":[24],"to":[26,31,42,53,79],"describe":[27],"our":[28],"in-progress":[29],"work":[30],"address":[32,81],"these":[33],"deficiencies.":[34],"We":[35,50],"start":[36],"with":[37,59],"Moroccan":[38],"Tunisian":[40],"dialects":[41],"provide":[43],"annotated":[44],"corpora":[45],"corpus-based":[47],"resources.":[49],"also":[51],"aim":[52],"extend":[54],"an":[55,72],"existing":[56],"morphological":[57,77],"engine":[58,78],"linguistic":[60,82],"built":[62],"ad":[63],"hoc":[64],"each":[66],"dialect.":[67],"In":[68],"addition,":[69],"we":[70],"develop":[71],"integrated":[73],"component":[74],"in":[75],"better":[80],"sociolinguistic":[84],"characteristics":[85],"while":[86],"preserving":[87],"integrity":[89],"dialectal":[91],"texts.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}
