{"id":"https://openalex.org/W1481490983","doi":"https://doi.org/10.63317/2v6fggyoqhpq","title":"An Automatically Built Named Entity Lexicon for Arabic","display_name":"An Automatically Built Named Entity Lexicon for Arabic","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W1481490983","doi":"https://doi.org/10.63317/2v6fggyoqhpq","mag":"1481490983"},"language":"en","primary_location":{"id":"doi:10.63317/2v6fggyoqhpq","doi":"https://doi.org/10.63317/2v6fggyoqhpq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2v6fggyoqhpq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/797_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/797_Paper.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075586667","display_name":"Mohammed A. Attia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mohammed Attia","raw_affiliation_strings":["NCLT , School of Computing , Dublin City University , Ireland","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCLT , School of Computing , Dublin City University , Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062029765","display_name":"Antonio Toral","orcid":"https://orcid.org/0000-0003-2357-2960","observed_orcids":["https://orcid.org/0000-0003-2357-2960"]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Antonio Toral","raw_affiliation_strings":["NCLT , School of Computing , Dublin City University , Ireland","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCLT , School of Computing , Dublin City University , Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000678794","display_name":"Lamia Tounsi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Lamia Tounsi","raw_affiliation_strings":["NCLT , School of Computing , Dublin City University , Ireland","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCLT , School of Computing , Dublin City University , Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084121304","display_name":"Monica Monachini","orcid":"https://orcid.org/0000-0003-3356-3988","observed_orcids":["https://orcid.org/0000-0003-3356-3988"]},"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/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE","IT"],"is_corresponding":false,"raw_author_name":"Monica Monachini","raw_affiliation_strings":["Istituto di Linguistica Computazionale , CNR , Pisa , Italy","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale , CNR , Pisa , Italy","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944","observed_orcids":["https://orcid.org/0000-0003-1322-7944"]},"institutions":[{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE","IT"],"is_corresponding":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":["NCLT , School of Computing , Dublin City University , Ireland","National Res. Council, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCLT , School of Computing , Dublin City University , Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"National Res. Council, Italy","institution_ids":["https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8758,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94647754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8647000193595886,"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":0.8647000193595886,"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":0.11209999769926071,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.012000000104308128,"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/named-entity-recognition","display_name":"named entity recognition","score":0.7450000047683716},{"id":"https://openalex.org/keywords/arabic-wordnet","display_name":"Arabic WordNet","score":0.925000011920929},{"id":"https://openalex.org/keywords/arabic-wikipedia","display_name":"Arabic Wikipedia","score":0.9789999723434448},{"id":"https://openalex.org/keywords/diacritization","display_name":"diacritization","score":0.7549999952316284},{"id":"https://openalex.org/keywords/geonames","display_name":"GeoNames","score":0.7590000033378601},{"id":"https://openalex.org/keywords/lexical-markup-framework","display_name":"Lexical Markup Framework","score":0.8889999985694885},{"id":"https://openalex.org/keywords/lexical-resources","display_name":"lexical resources","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9157260060310364},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7667437195777893},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.6271759271621704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.614479660987854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357761383056641},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4819471836090088},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4586934447288513},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4304695129394531},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2586206793785095},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.63317/2v6fggyoqhpq","doi":"https://doi.org/10.63317/2v6fggyoqhpq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2v6fggyoqhpq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/797_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:http://www.rian.ie/44936/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15979/","pdf_url":"http://doras.dcu.ie/15979/","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Attia, Mohammed, Toral, Antonio ORCID: 0000-0003-2357-2960 &lt;https://orcid.org/0000-0003-2357-2960&gt;, Tounsi, Lamia, Monachini, Monica and van Genabith, Josef (2010) An automatically built named entity lexicon for Arabic. In: LREC 2010 - 7th conference on International Language Resources and Evaluation, 17-23 May 2010, Valletta, Malta.","raw_type":"Other"},{"id":"pmh:oai:doras.dcu.ie:15979","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0003-2357-2960>,","pdf_url":"https://doras.dcu.ie/15979/1/An_automatically_built_Named_Entity_lexicon_for_Arabic.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.1098","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.1098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/797_Paper.pdf","raw_type":"text"},{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.ilc/cnr.ilc/2010-A2-011","doi":null,"is_oa":false,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.ilc/cnr.ilc/2010-A2-011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: LREC'10 - Seventh International Conference on Language Resources and Evaluation (Valletta, Malta, 17-23 May 2010). Proceedings, pp. 3614 - 3621. Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:1481490983","doi":null,"is_oa":false,"landing_page_url":"http://doras.dcu.ie/15979/1/An_automatically_built_Named_Entity_lexicon_for_Arabic.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/2v6fggyoqhpq","doi":"https://doi.org/10.63317/2v6fggyoqhpq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2v6fggyoqhpq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/797_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G892338402","display_name":"Platform for Automatic, Normalized Annotation and Cost-Effective Acquisition of Language Resources for Human Language Technologies","funder_award_id":"248064","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320834","display_name":"Enterprise Ireland","ror":"https://ror.org/023z51242"},{"id":"https://openalex.org/F4320320842","display_name":"Irish Research Council for Science, Engineering and Technology","ror":null},{"id":"https://openalex.org/F4320321056","display_name":"Irish Research Council","ror":"https://ror.org/051xex213"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1481490983.pdf","grobid_xml":"https://content.openalex.org/works/W1481490983.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W45643337","https://openalex.org/W68059783","https://openalex.org/W125728403","https://openalex.org/W184563370","https://openalex.org/W340195604","https://openalex.org/W1505506221","https://openalex.org/W1508361643","https://openalex.org/W1520131719","https://openalex.org/W1537506313","https://openalex.org/W1565814412","https://openalex.org/W1596967103","https://openalex.org/W1965475126","https://openalex.org/W1992004647","https://openalex.org/W2022414723","https://openalex.org/W2041349462","https://openalex.org/W2056382745","https://openalex.org/W2100976324","https://openalex.org/W2148398225","https://openalex.org/W2344189264","https://openalex.org/W2757950651","https://openalex.org/W2779285644"],"related_works":["https://openalex.org/W2253822010","https://openalex.org/W2250865411","https://openalex.org/W2752855602","https://openalex.org/W2787423230","https://openalex.org/W7099971265","https://openalex.org/W3096082174","https://openalex.org/W1974243903","https://openalex.org/W2782553531","https://openalex.org/W2123671373","https://openalex.org/W2033599040"],"abstract_inverted_index":{"We":[0],"have":[1,74,122,148],"successfully":[2],"adapted":[3],"and":[4,20,29,34,109,128,140,150,165,177],"extended":[5],"the":[6,31,80,131,136,155,169],"automatic":[7],"Multilingual,":[8],"Interoperable":[9],"Named":[10,57],"Entity":[11],"Lexicon":[12],"approach":[13],"to":[14,44,55,66,89,130,146,186,192],"Arabic,":[15],"using":[16,102],"Arabic":[17,21,69,117,126,142],"WordNet":[18],"(AWN)":[19],"Wikipedia":[22,41],"(AWK).First,":[23],"we":[24,39,84,99,121],"extract":[25],"AWN's":[26],"instantiable":[27],"nouns":[28],"identify":[30,56],"corresponding":[32],"categories":[33],"hyponym":[35],"subcategories":[36],"in":[37,49,53,77],"AWK.Then,":[38],"exploit":[40],"inter-lingual":[42],"links":[43],"locate":[45],"correspondences":[46],"between":[47],"articles":[48,70],"ten":[50],"different":[51,110,193],"languages":[52],"order":[54],"Entities":[58],"(NEs).We":[59],"apply":[60],"keyword":[61],"search":[62],"on":[63],"AWK":[64,94],"abstracts":[65],"provide":[67],"for":[68,112],"that":[71],"do":[72],"not":[73,95],"a":[75,86,163,172,196],"correspondence":[76],"any":[78],"of":[79,116,133,168,195],"other":[81],"languages.In":[82],"addition,":[83],"perform":[85],"post-processing":[87],"step":[88],"fetch":[90],"further":[91],"NEs":[92,127],"from":[93,181],"reachable":[96],"through":[97],"AWN.Finally,":[98],"investigate":[100],"diacritization":[101],"matching":[103],"with":[104],"geonames":[105],"databases,":[106],"MADA-TOKAN":[107],"tools":[108],"heuristics":[111],"restoring":[113],"vowel":[114],"marks":[115],"NEs.Using":[118],"this":[119,152],"methodology,":[120],"extracted":[123],"approximately":[124],"45,000":[125],"built,":[129],"best":[132],"our":[134],"knowledge,":[135],"largest,":[137],"most":[138],"mature":[139],"well-structured":[141],"NE":[143],"lexical":[144],"resource":[145],"date.We":[147],"stored":[149],"organised":[151],"lexicon":[153,170],"following":[154],"Lexical":[156],"Markup":[157],"Framework":[158],"(LMF)":[159],"ISO":[160],"standard.We":[161],"conduct":[162],"quantitative":[164],"qualitative":[166],"evaluation":[167],"against":[171],"manually":[173],"annotated":[174],"gold":[175],"standard":[176],"achieve":[178],"precision":[179],"scores":[180],"95.83%":[182],"(with":[183,188],"66.13%":[184],"recall)":[185,190],"99.31%":[187],"61.45%":[189],"according":[191],"values":[194],"threshold.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2016-06-24T00:00:00"}
