{"id":"https://openalex.org/W2251212642","doi":"https://doi.org/10.18653/v1/w15-3209","title":"A Pilot Study on Arabic Multi-Genre Corpus Diacritization","display_name":"A Pilot Study on Arabic Multi-Genre Corpus Diacritization","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251212642","doi":"https://doi.org/10.18653/v1/w15-3209","mag":"2251212642"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3209","pdf_url":"https://www.aclweb.org/anthology/W15-3209.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 Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3209.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078234452","display_name":"Houda Bouamor","orcid":"https://orcid.org/0000-0001-8605-957X"},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Houda Bouamor","raw_affiliation_strings":["Carnegie Mellon University in Qatar;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar;","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047390057","display_name":"Wajdi Zaghouani","orcid":"https://orcid.org/0000-0003-1521-5568"},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Wajdi Zaghouani","raw_affiliation_strings":["Carnegie Mellon University in Qatar;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar;","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Diab","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080300851","display_name":"Ossama Obeid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ossama Obeid","raw_affiliation_strings":["Carnegie Mellon University in Qatar;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar;","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003566053","display_name":"Kemal Oflazer","orcid":"https://orcid.org/0000-0002-4977-0079"},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Kemal Oflazer","raw_affiliation_strings":["Carnegie Mellon University in Qatar;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar;","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061244688","display_name":"Mahmoud Ghoneim","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmoud Ghoneim","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038069921","display_name":"Abdelati Hawwari","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelati Hawwari","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9983999729156494,"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":0.8288695812225342},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8256473541259766},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7473655939102173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7102810740470886},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.6466677188873291},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5814613699913025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723210573196411},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3433346450328827},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.08204624056816101},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06165763735771179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288695812225342},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8256473541259766},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7473655939102173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7102810740470886},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.6466677188873291},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5814613699913025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723210573196411},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3433346450328827},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.08204624056816101},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06165763735771179},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-3209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3209","pdf_url":"https://www.aclweb.org/anthology/W15-3209.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 Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3209","pdf_url":"https://www.aclweb.org/anthology/W15-3209.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 Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8093557049","display_name":null,"funder_award_id":"NPRP-6","funder_id":"https://openalex.org/F4320309815","funder_display_name":"Qatar Foundation"}],"funders":[{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251212642.pdf","grobid_xml":"https://content.openalex.org/works/W2251212642.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1538879546","https://openalex.org/W1565703351","https://openalex.org/W1972404024","https://openalex.org/W2009639677","https://openalex.org/W2011402185","https://openalex.org/W2012804051","https://openalex.org/W2020079054","https://openalex.org/W2057622292","https://openalex.org/W2100976324","https://openalex.org/W2109613320","https://openalex.org/W2126784811","https://openalex.org/W2153186553","https://openalex.org/W2250816155","https://openalex.org/W2526376940","https://openalex.org/W3202110839","https://openalex.org/W4245136196"],"related_works":["https://openalex.org/W2349956239","https://openalex.org/W2522162613","https://openalex.org/W2393217036","https://openalex.org/W4206957170","https://openalex.org/W2184509518","https://openalex.org/W2080283158","https://openalex.org/W3183814539","https://openalex.org/W4243842732","https://openalex.org/W4388778088","https://openalex.org/W137214525"],"abstract_inverted_index":{"Arabic":[0,38,61],"script":[1,39],"writing":[2],"is":[3,46],"typically":[4],"underspecified":[5],"for":[6],"short":[7],"vowels":[8],"and":[9,114],"other":[10,30],"mark":[11],"up,":[12],"referred":[13],"to":[14,26,106],"as":[15],"diacritics.":[16],"Apart":[17],"from":[18,88],"the":[19,32,50,102,107,121,124,137],"lexical":[20],"ambiguity":[21,44],"found":[22],"in":[23,29,36,78,136],"words,":[24],"similar":[25],"that":[27],"exhibited":[28],"languages,":[31],"lack":[33],"of":[34,43,49,53,84,123],"diacritics":[35],"written":[37,54],"adds":[40],"another":[41],"layer":[42],"which":[45],"an":[47],"artifact":[48],"orthography.":[51],"Diacritization":[52],"text":[55,90],"has":[56],"a":[57,69,74,82],"significant":[58],"impact":[59,122],"on":[60,72,127],"NLP":[62],"applications.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,99,131],"present":[68,100,120],"pilot":[70],"study":[71,132],"building":[73],"diacritized":[75,117],"multi-genre":[76],"corpus":[77],"Arabic.":[79],"We":[80,92,119],"annotate":[81],"sample":[83],"nondiacritized":[85],"words":[86],"extracted":[87],"five":[89],"genres.":[91],"explore":[93],"different":[94,133],"annotation":[95,125,128],"strategies:":[96],"Basic":[97],"where":[98],"only":[101],"bare":[103],"undiacritized":[104],"forms":[105],"annotators,":[108],"Intermediate":[109],"(Basic":[110],"forms+their":[111],"POS":[112],"tags),":[113],"Advanced":[115],"(automatically":[116],"words).":[118],"strategy":[126],"quality.":[129],"Moreover,":[130],"diacritization":[134],"schemes":[135],"process.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
