{"id":"https://openalex.org/W4406891914","doi":"https://doi.org/10.1109/fllm63129.2024.10852494","title":"Enhancing Named Entity Recognition in Arabic: Leveraging Transformer-Based Models and Open Data Sources","display_name":"Enhancing Named Entity Recognition in Arabic: Leveraging Transformer-Based Models and Open Data Sources","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406891914","doi":"https://doi.org/10.1109/fllm63129.2024.10852494"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","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/A5002094258","display_name":"Faiza Belbachir","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116658","display_name":"\u00c9cole Centrale d'\u00c9lectronique","ror":"https://ror.org/02k6n4s14","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210116658"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Faiza Belbachir","raw_affiliation_strings":["Laboratoire de Recherche LYRIDS,Ecole d’ingénieurs Campus de Paris (ECE),Paris,France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Recherche LYRIDS,Ecole d’ingénieurs Campus de Paris (ECE),Paris,France","institution_ids":["https://openalex.org/I4210116658"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032398749","display_name":"Assia Soukane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116658","display_name":"\u00c9cole Centrale d'\u00c9lectronique","ror":"https://ror.org/02k6n4s14","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210116658"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Assia Soukane","raw_affiliation_strings":["Laboratoire de Recherche LYRIDS,Ecole d’ingénieurs Campus de Paris (ECE),Paris,France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Recherche LYRIDS,Ecole d’ingénieurs Campus de Paris (ECE),Paris,France","institution_ids":["https://openalex.org/I4210116658"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002094258"],"corresponding_institution_ids":["https://openalex.org/I4210116658"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78391317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9815999865531921,"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/computer-science","display_name":"Computer science","score":0.7784812450408936},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6562145352363586},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6235252618789673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5305168032646179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4860420823097229},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.48035940527915955},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4595905542373657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3234773576259613},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1214551329612732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12049350142478943},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08369845151901245},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07930922508239746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07705840468406677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784812450408936},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6562145352363586},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6235252618789673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5305168032646179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860420823097229},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.48035940527915955},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4595905542373657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3234773576259613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1214551329612732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12049350142478943},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08369845151901245},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07930922508239746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07705840468406677},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3199871245","https://openalex.org/W2915436880","https://openalex.org/W1964783010","https://openalex.org/W3198729192","https://openalex.org/W3121292129","https://openalex.org/W4249048193","https://openalex.org/W4295038225","https://openalex.org/W4285819037","https://openalex.org/W3000360420","https://openalex.org/W3115058362"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,40,84],"present":[4],"our":[5,33],"system\u2019s":[6],"design,":[7],"focusing":[8],"on":[9,62],"named":[10],"entity":[11],"recognition":[12],"(NER)":[13],"in":[14,37],"the":[15,46,63,77,86,117],"Arabic":[16,90],"language.":[17],"Our":[18,105],"approach":[19],"employs":[20],"a":[21,42],"transformer-based":[22],"language":[23],"model,":[24],"augmented":[25],"with":[26,35],"data":[27,92],"from":[28,95],"open":[29,91],"sources.":[30],"We":[31],"report":[32],"experiments":[34],"NER":[36],"Arabic,":[38],"where":[39],"conduct":[41],"comparative":[43],"analysis":[44],"of":[45,68,88,114,126],"performance":[47],"between":[48],"CamelBERT":[49],"and":[50,56,65,98],"two":[51],"other":[52],"models,":[53],"namely":[54],"UBC-NLP-ArBert2":[55],"AraBERTv02.":[57],"This":[58],"evaluation":[59],"is":[60],"performed":[61],"training":[64],"development":[66],"datasets":[67],"Subtask":[69],"1":[70],"FLAT-NER":[71],"for":[72],"non-nested":[73],"entities,":[74],"proposed":[75],"by":[76],"WojoodNER":[78],"Shared":[79],"Task":[80],"2023":[81],"[1].":[82],"Furthermore,":[83],"investigate":[85],"impact":[87],"incorporating":[89],"sources":[93],"extracted":[94],"AQMAR":[96],"[2]":[97],"ANERcorp":[99],"[3]":[100],"through":[101],"post-processing":[102],"lexical":[103],"filtering.":[104],"system":[106],"demonstrates":[107],"promising":[108],"results,":[109],"achieving":[110],"an":[111,123],"F1":[112,124],"score":[113,125],"0.9112,":[115],"surpassing":[116],"organizers\u2019":[118],"baseline":[119],"performance,":[120],"which":[121],"yielded":[122],"0.8681.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}