{"id":"https://openalex.org/W4377989177","doi":"https://doi.org/10.1145/3599234","title":"Tokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models","display_name":"Tokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4377989177","doi":"https://doi.org/10.1145/3599234"},"language":"en","primary_location":{"id":"doi:10.1145/3599234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3599234","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5015786241","display_name":"Asma Mekki","orcid":"https://orcid.org/0000-0003-3140-3171"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Asma Mekki","raw_affiliation_strings":["ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia"],"raw_orcid":"https://orcid.org/0000-0003-3140-3171","affiliations":[{"raw_affiliation_string":"ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037847102","display_name":"In\u00e8s Zribi","orcid":"https://orcid.org/0000-0002-2065-7873"},"institutions":[{"id":"https://openalex.org/I166928557","display_name":"University of Monastir","ror":"https://ror.org/00nhtcg76","country_code":"TN","type":"education","lineage":["https://openalex.org/I166928557"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"In\u00e8s Zribi","raw_affiliation_strings":["ANLP Research Group, MIRACL Lab., ISIMa, University of Monastir, Tunisia"],"raw_orcid":"https://orcid.org/0000-0002-2065-7873","affiliations":[{"raw_affiliation_string":"ANLP Research Group, MIRACL Lab., ISIMa, University of Monastir, Tunisia","institution_ids":["https://openalex.org/I166928557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mariem Ellouze","orcid":"https://orcid.org/0000-0003-1864-2602"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Mariem Ellouze","raw_affiliation_strings":["ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia"],"raw_orcid":"https://orcid.org/0000-0003-1864-2602","affiliations":[{"raw_affiliation_string":"ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001984598","display_name":"Lamia Hadrich Belguith","orcid":"https://orcid.org/0000-0002-4868-657X"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Lamia Hadrich Belguith","raw_affiliation_strings":["ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia"],"raw_orcid":"https://orcid.org/0000-0002-4868-657X","affiliations":[{"raw_affiliation_string":"ANLP Research Group, MIRACL Lab., University of Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015786241"],"corresponding_institution_ids":["https://openalex.org/I142899784"],"apc_list":null,"apc_paid":null,"fwci":0.8284,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77665704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T13629","display_name":"Text Readability and Simplification","score":0.9937999844551086,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9152296781539917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8344481587409973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7584959268569946},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7502973079681396},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6326228976249695},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5914412140846252},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5589658617973328},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.538396418094635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49875807762145996},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.4535554051399231},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4449538290500641},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1700897216796875}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9152296781539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344481587409973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7584959268569946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7502973079681396},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6326228976249695},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5914412140846252},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5589658617973328},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.538396418094635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49875807762145996},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4535554051399231},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4449538290500641},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1700897216796875},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3599234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3599234","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W72487590","https://openalex.org/W146945658","https://openalex.org/W151307157","https://openalex.org/W1524281572","https://openalex.org/W1966863499","https://openalex.org/W2049151043","https://openalex.org/W2153579005","https://openalex.org/W2156909104","https://openalex.org/W2169160736","https://openalex.org/W2326206218","https://openalex.org/W2395245243","https://openalex.org/W2471147443","https://openalex.org/W2581564515","https://openalex.org/W2585813550","https://openalex.org/W2606443730","https://openalex.org/W2612649659","https://openalex.org/W2737249384","https://openalex.org/W2799915114","https://openalex.org/W2890395128","https://openalex.org/W2891295164","https://openalex.org/W2912165583","https://openalex.org/W3115439509","https://openalex.org/W3156641572","https://openalex.org/W3167628632","https://openalex.org/W4294170691","https://openalex.org/W4297198909","https://openalex.org/W4299828299","https://openalex.org/W6733377360"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W2151197196","https://openalex.org/W1619002","https://openalex.org/W4292346028","https://openalex.org/W2725310424","https://openalex.org/W4282591925","https://openalex.org/W2963023579","https://openalex.org/W4287760117","https://openalex.org/W3045818198","https://openalex.org/W3034697300"],"abstract_inverted_index":{"Tokenization":[0],"represents":[1],"the":[2,63,66,79,82,87],"way":[3],"of":[4,8,65,81,114,143],"segmenting":[5],"a":[6,26,58,112],"piece":[7],"text":[9],"into":[10],"smaller":[11],"units":[12],"called":[13],"tokens.":[14],"Since":[15],"Arabic":[16,75],"is":[17,86],"an":[18,140],"agglutinating":[19],"language":[20],"by":[21,99],"nature,":[22],"this":[23,50,69,85],"treatment":[24],"becomes":[25],"crucial":[27],"preprocessing":[28],"step":[29],"for":[30,93],"many":[31],"Natural":[32],"Language":[33],"Processing":[34],"(NLP)":[35],"applications":[36],"such":[37],"as":[38],"morphological":[39],"analysis,":[40],"parsing,":[41],"machine":[42],"translation,":[43],"information":[44],"extraction,":[45],"and":[46,101,128],"so":[47],"on.":[48],"In":[49],"article,":[51],"we":[52,71,97,110],"investigate":[53],"word":[54,94],"tokenization":[55],"task":[56],"with":[57],"rewriting":[59],"process":[60],"to":[61],"rewrite":[62],"orthography":[64],"stem.":[67],"For":[68],"task,":[70],"are":[72],"using":[73,137],"Tunisian":[74],"(TA)":[76],"text.":[77],"To":[78],"best":[80,134],"researchers\u2019":[83],"knowledge,":[84],"first":[88],"study":[89],"that":[90],"uses":[91],"TA":[92,104],"tokenization.":[95],"Therefore,":[96],"start":[98],"collecting":[100],"preparing":[102],"various":[103],"corpora":[105],"from":[106],"different":[107],"sources.":[108],"Then,":[109],"present":[111],"comparison":[113],"three":[115],"character-based":[116],"tokenizers":[117],"based":[118],"on":[119],"Conditional":[120],"Random":[121],"Fields":[122],"(CRF),":[123],"Support":[124],"Vector":[125],"Machines":[126],"(SVM)":[127],"Deep":[129],"Neural":[130],"Networks":[131],"(DNN).":[132],"The":[133],"proposed":[135],"model":[136],"CRF":[138],"achieved":[139],"F-measure":[141],"result":[142],"88.9%.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}