{"id":"https://openalex.org/W785060174","doi":"https://doi.org/10.3115/v1/e14-3012","title":"Automatic Creation of Arabic Named Entity Annotated Corpus Using Wikipedia","display_name":"Automatic Creation of Arabic Named Entity Annotated Corpus Using Wikipedia","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W785060174","doi":"https://doi.org/10.3115/v1/e14-3012","mag":"785060174"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-3012","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3012","pdf_url":"https://aclanthology.org/E14-3012.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-3012.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049157081","display_name":"Maha Jarallah Althobaiti","orcid":"https://orcid.org/0000-0002-8734-4011"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Maha Althobaiti","raw_affiliation_strings":["School of Computer Science and Electronic Engineering University of Essex Colchester, UK","University of Essex, Colchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering University of Essex Colchester, UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"University of Essex, Colchester, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014534985","display_name":"Udo Kruschwitz","orcid":"https://orcid.org/0000-0002-5503-0341"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Udo Kruschwitz","raw_affiliation_strings":["School of Computer Science and Electronic Engineering University of Essex Colchester, UK","University of Essex, Colchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering University of Essex Colchester, UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"University of Essex, Colchester, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047065550","display_name":"Massimo Poesio","orcid":"https://orcid.org/0000-0001-8469-2072"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimo Poesio","raw_affiliation_strings":["School of Computer Science and Electronic Engineering University of Essex Colchester, UK","University of Essex **"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering University of Essex Colchester, UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"University of Essex **","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049157081"],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":4.2201,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94163066,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"106","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788560152053833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7070466876029968},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6322954893112183},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5592359900474548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565497279167175},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47850504517555237},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32664722204208374},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2750789523124695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788560152053833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7070466876029968},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6322954893112183},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5592359900474548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565497279167175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47850504517555237},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32664722204208374},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2750789523124695},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/e14-3012","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3012","pdf_url":"https://aclanthology.org/E14-3012.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.essex.ac.uk:11980","is_oa":true,"landing_page_url":null,"pdf_url":"http://repository.essex.ac.uk/11980/1/document.pdf","source":{"id":"https://openalex.org/S4306401236","display_name":"Open Access at Essex (University of Essex)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I110002522","host_organization_name":"University of Essex","host_organization_lineage":["https://openalex.org/I110002522"],"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":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-3012","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3012","pdf_url":"https://aclanthology.org/E14-3012.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W785060174.pdf","grobid_xml":"https://content.openalex.org/works/W785060174.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W130452239","https://openalex.org/W630883066","https://openalex.org/W1502473750","https://openalex.org/W1728883788","https://openalex.org/W1814730318","https://openalex.org/W2022414723","https://openalex.org/W2033937535","https://openalex.org/W2061351603","https://openalex.org/W2099253769","https://openalex.org/W2104912629","https://openalex.org/W2120844411","https://openalex.org/W2140428995","https://openalex.org/W2141099517","https://openalex.org/W2144934730","https://openalex.org/W2163918411","https://openalex.org/W2177399422","https://openalex.org/W2250402023","https://openalex.org/W2250783611","https://openalex.org/W2251330961","https://openalex.org/W2252061787","https://openalex.org/W4302585900"],"related_works":["https://openalex.org/W4390279576","https://openalex.org/W2146948107","https://openalex.org/W2485077425","https://openalex.org/W2149657908","https://openalex.org/W2281456995","https://openalex.org/W3128216712","https://openalex.org/W2251062999","https://openalex.org/W2606919896","https://openalex.org/W2098057544","https://openalex.org/W2066586317"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,66,80],"propose":[4],"a":[5,69,83],"new":[6,117],"methodology":[7],"to":[8,14,37,54,72,94,99,123],"exploit":[9],"Wikipedia":[10,23,43,63,91],"features":[11,44],"and":[12,49,107],"structure":[13],"automatically":[15],"develop":[16],"an":[17,28,125,139],"Arabic":[18,103],"NE":[19,29,40,126,140],"annotated":[20,152],"corpus.":[21],"Each":[22],"link":[24],"is":[25],"transformed":[26],"into":[27],"type":[30],"of":[31,90,110],"the":[32,39,87,108,137],"target":[33],"article":[34],"in":[35,62,92,102],"order":[36,93],"produce":[38],"annotation.":[41],"Other":[42],"-namely":[45],"redirects,":[46],"anchor":[47],"texts,":[48],"inter-language":[50],"links":[51,61],"-are":[52],"used":[53,122],"tag":[55],"additional":[56],"NEs,":[57],"which":[58,128],"appear":[59],"without":[60],"texts.":[64],"Furthermore,":[65],"have":[67],"developed":[68],"filtering":[70],"algorithm":[71],"eliminate":[73],"ambiguity":[74],"when":[75],"tagging":[76,100],"candidate":[77],"NEs.":[78],"Herein":[79],"also":[81],"introduce":[82],"mechanism":[84],"based":[85],"on":[86,132,143,150],"high":[88],"coverage":[89],"address":[95],"two":[96],"challenges":[97],"particular":[98],"NEs":[101],"text:":[104],"rich":[105],"morphology":[106],"absence":[109],"capitalisation.":[111],"The":[112],"corpus":[113],"created":[114],"with":[115,147],"our":[116],"method":[118],"(WDC)":[119],"has":[120,129],"been":[121,130],"train":[124],"tagger":[127,141],"tested":[131],"different":[133],"domains.":[134],"Judging":[135],"by":[136],"results,":[138],"trained":[142,149],"WDC":[144],"can":[145],"compete":[146],"those":[148],"manually":[151],"corpora.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
