{"id":"https://openalex.org/W4406137491","doi":"https://doi.org/10.1109/ojcs.2025.3526712","title":"Comparative Analysis of Traditional and Modern NLP Techniques on the CoLA Dataset: From POS Tagging to Large Language Models","display_name":"Comparative Analysis of Traditional and Modern NLP Techniques on the CoLA Dataset: From POS Tagging to Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406137491","doi":"https://doi.org/10.1109/ojcs.2025.3526712"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2025.3526712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3526712","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2025.3526712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091227632","display_name":"Abdessamad Benlahbib","orcid":"https://orcid.org/0000-0002-0039-7832"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Abdessamad Benlahbib","raw_affiliation_strings":["Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco"],"raw_orcid":"https://orcid.org/0000-0002-0039-7832","affiliations":[{"raw_affiliation_string":"Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029227382","display_name":"Achraf Boumhidi","orcid":"https://orcid.org/0000-0002-7396-9651"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Achraf Boumhidi","raw_affiliation_strings":["Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco"],"raw_orcid":"https://orcid.org/0000-0002-7396-9651","affiliations":[{"raw_affiliation_string":"Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036279867","display_name":"Anass Fahfouh","orcid":"https://orcid.org/0000-0001-5793-0725"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Anass Fahfouh","raw_affiliation_strings":["Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco"],"raw_orcid":"https://orcid.org/0000-0001-5793-0725","affiliations":[{"raw_affiliation_string":"Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028888571","display_name":"Hamza Alami","orcid":"https://orcid.org/0000-0001-6945-6098"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hamza Alami","raw_affiliation_strings":["Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco"],"raw_orcid":"https://orcid.org/0000-0001-6945-6098","affiliations":[{"raw_affiliation_string":"Computer Science Department, LISAC Laboratory, Faculty of Sciences Dhar EL Mehraz (F.S.D.M), Sidi Mohamed Ben Abdellah University, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I81605866"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":6.98,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96148128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"248","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9480999708175659,"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":0.9480999708175659,"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/cola","display_name":"Cola (plant)","score":0.7688482999801636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7378683686256409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6785414218902588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.615479052066803},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40736839175224304},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10074228048324585},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07480350136756897}],"concepts":[{"id":"https://openalex.org/C2781138811","wikidata":"https://www.wikidata.org/wiki/Q114264","display_name":"Cola (plant)","level":2,"score":0.7688482999801636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7378683686256409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6785414218902588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.615479052066803},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40736839175224304},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10074228048324585},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07480350136756897},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2025.3526712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3526712","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f0c226bc8b2b439ebd40eba10d19d977","is_oa":true,"landing_page_url":"https://doaj.org/article/f0c226bc8b2b439ebd40eba10d19d977","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 6, Pp 248-260 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2025.3526712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3526712","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2064675550","https://openalex.org/W2122111042","https://openalex.org/W2250539671","https://openalex.org/W2295598076","https://openalex.org/W2903950532","https://openalex.org/W2923014074","https://openalex.org/W2950635152","https://openalex.org/W2953356739","https://openalex.org/W3034999214","https://openalex.org/W4239510810","https://openalex.org/W4288953700","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6632865047","https://openalex.org/W6665546858","https://openalex.org/W6676552512","https://openalex.org/W6723250868","https://openalex.org/W6745609711","https://openalex.org/W6748634344","https://openalex.org/W6752342493","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6776565550","https://openalex.org/W6778883912","https://openalex.org/W6779068807","https://openalex.org/W6781389535","https://openalex.org/W6787814785","https://openalex.org/W6803557570","https://openalex.org/W6810464575","https://openalex.org/W6838405681","https://openalex.org/W6846435535","https://openalex.org/W6847118041","https://openalex.org/W6851779688"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2003247564","https://openalex.org/W2419991450","https://openalex.org/W2406159221","https://openalex.org/W2910679271","https://openalex.org/W2049009785","https://openalex.org/W4313025928","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"task":[1,45],"of":[2,11,41,58,155,168],"classifying":[3],"linguistic":[4],"acceptability,":[5],"exemplified":[6],"by":[7,130],"the":[8,44,152,166],"CoLA":[9],"(Corpus":[10],"Linguistic":[12],"Acceptability)":[13],"dataset,":[14],"poses":[15],"unique":[16],"challenges":[17,25],"for":[18,48,158],"natural":[19],"language":[20],"processing":[21],"(NLP)":[22],"models.":[23],"These":[24],"include":[26],"distinguishing":[27],"between":[28],"subtle":[29],"grammatical":[30],"errors,":[31],"understanding":[32],"complex":[33],"syntactic":[34],"structures,":[35],"and":[36,68,80,88,102,142,162],"detecting":[37],"semantic":[38,163],"inconsistencies,":[39],"all":[40],"which":[42],"make":[43],"difficult":[46],"even":[47],"human":[49],"annotators.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"compare":[55],"a":[56,110],"range":[57],"techniques,":[59],"from":[60,90,118],"traditional":[61,119],"methods":[62,71],"such":[63,85],"as":[64,86,94,96,115],"Part-of-Speech":[65],"(POS)":[66],"tagging":[67],"feature":[69],"extraction":[70],"like":[72,100],"CountVectorizer":[73],"with":[74,133,139],"Term":[75],"Frequency-Inverse":[76],"Document":[77],"Frequency":[78],"(TF-IDF)":[79],"N-grams,":[81],"to":[82,120],"modern":[83],"embeddings":[84],"FastText":[87],"Embeddings":[89],"Language":[91,104],"Models":[92,105],"(ELMo),":[93],"well":[95],"deep":[97],"learning":[98],"architectures":[99],"transformers":[101],"Large":[103],"(LLMs).":[106],"Our":[107],"experiments":[108],"show":[109],"clear":[111],"improvement":[112],"in":[113,170],"performance":[114],"models":[116],"evolve":[117],"more":[121],"advanced":[122],"approaches.":[123],"Notably,":[124],"state-of-the-art":[125],"(SOTA)":[126],"results":[127],"were":[128],"obtained":[129],"fine-tuning":[131],"GPT-4o":[132],"extensive":[134],"hyperparameter":[135],"tuning,":[136],"including":[137],"experimenting":[138],"various":[140],"epochs":[141],"batch":[143],"sizes.":[144],"This":[145],"comparative":[146],"analysis":[147],"provides":[148],"valuable":[149],"insights":[150],"into":[151],"relative":[153],"strengths":[154],"each":[156],"technique":[157],"identifying":[159],"morphological,":[160],"syntactic,":[161],"violations,":[164],"highlighting":[165],"effectiveness":[167],"LLMs":[169],"these":[171],"tasks.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}