{"id":"https://openalex.org/W6891746348","doi":"https://doi.org/10.48448/6tcg-bv77","title":"A Semi-Supervised BERT Approach for Arabic Named Entity Recognition","display_name":"A Semi-Supervised BERT Approach for Arabic Named Entity Recognition","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W6891746348","doi":"https://doi.org/10.48448/6tcg-bv77","mag":"3120332616"},"language":"en","primary_location":{"id":"doi:10.48448/6tcg-bv77","doi":"https://doi.org/10.48448/6tcg-bv77","is_oa":true,"landing_page_url":"https://doi.org/10.48448/6tcg-bv77","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/6tcg-bv77","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"The 28th International Conference on Computational Linguistics 2020","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"The 28th International Conference on Computational Linguistics 2020","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dib, Ghassan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dib, Ghassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343355","display_name":"Shady Elbassuoni","orcid":"https://orcid.org/0000-0002-3491-6311","observed_orcids":["https://orcid.org/0000-0002-3491-6311"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elbassuoni   , Shady","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079100236","display_name":"Chadi Helwe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helwe, Chadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000294197","display_name":"Mohsen Shamas","orcid":"https://orcid.org/0000-0001-5614-7587","observed_orcids":["https://orcid.org/0000-0001-5614-7587"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shamas, Mohsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.0013000000035390258,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/arabic-named-entity-recognition","display_name":"Arabic named entity recognition","score":0.9319999814033508},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9789999723434448},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.968999981880188},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.9089999794960022},{"id":"https://openalex.org/keywords/tweets","display_name":"tweets","score":0.5049999952316284}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.9452999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990000247955322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7524999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7013000249862671},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5299999713897705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.26739999651908875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.48448/6tcg-bv77","doi":"https://doi.org/10.48448/6tcg-bv77","is_oa":true,"landing_page_url":"https://doi.org/10.48448/6tcg-bv77","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"mag:3120332616","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wanlp-1.5.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.48448/6tcg-bv77","doi":"https://doi.org/10.48448/6tcg-bv77","is_oa":true,"landing_page_url":"https://doi.org/10.48448/6tcg-bv77","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7571463584899902,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7134692502","https://openalex.org/W3140747828","https://openalex.org/W4408984947","https://openalex.org/W3100530666","https://openalex.org/W2773616286","https://openalex.org/W2405861896","https://openalex.org/W2971341430","https://openalex.org/W4415969721","https://openalex.org/W4290928096","https://openalex.org/W4386938013"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition":[2],"(NER)":[3],"plays":[4],"a":[5,51,57,87],"significant":[6,88],"role":[7],"in":[8,90,102,120],"many":[9,126],"applications":[10],"such":[11],"as":[12],"information":[13,15],"extraction,":[14],"retrieval,":[16],"question":[17],"answering,":[18],"and":[19,39,41,63,73,83,95,107,124],"even":[20],"machine":[21],"translation.":[22],"Most":[23],"of":[24],"the":[25,93,96,111,121],"work":[26],"on":[27,46,78],"NER":[28,59,76],"using":[29,61],"deep":[30],"learning":[31,53],"was":[32],"done":[33],"for":[34,92,110],"non-Arabic":[35],"languages":[36],"like":[37],"English":[38],"French,":[40],"only":[42],"few":[43],"studies":[44],"focused":[45],"Arabic.":[47],"This":[48],"paper":[49],"proposes":[50],"semi-supervised":[52],"approach":[54,69],"to":[55],"train":[56],"BERT-based":[58],"model":[60],"labeled":[62],"semi-labeled":[64],"datasets.":[65],"We":[66,85],"compared":[67],"our":[68],"against":[70],"various":[71],"baselines,":[72],"state-of-the-art":[74],"Arabic":[75,105],"tools":[77],"three":[79],"datasets:":[80],"AQMAR,":[81],"NEWS,":[82],"TWEETS.":[84],"report":[86],"improvement":[89],"F-measure":[91],"AQMAR":[94],"NEWS":[97],"datasets,":[98],"which":[99,114],"are":[100,118],"written":[101],"Modern":[103],"Standard":[104],"(MSA),":[106],"competitive":[108],"results":[109],"TWEETS":[112],"dataset,":[113],"contains":[115],"tweets":[116],"that":[117],"mostly":[119],"Egyptian":[122],"dialect":[123],"contain":[125],"mistakes":[127],"or":[128],"misspellings.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
