{"id":"https://openalex.org/W2065400286","doi":"https://doi.org/10.3115/1621774.1621780","title":"A hybrid approach for building Arabic diacritizer","display_name":"A hybrid approach for building Arabic diacritizer","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2065400286","doi":"https://doi.org/10.3115/1621774.1621780","mag":"2065400286"},"language":"en","primary_location":{"id":"doi:10.3115/1621774.1621780","doi":"https://doi.org/10.3115/1621774.1621780","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621774.1621780","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621774.1621780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EACL 2009 Workshop on Computational Approaches to Semitic Languages - Semitic '09","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.5555/1621774.1621780","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066945309","display_name":"Khaled F. Shaalan","orcid":"https://orcid.org/0000-0003-0823-8390","observed_orcids":["https://orcid.org/0000-0003-0823-8390"]},"institutions":[{"id":"https://openalex.org/I193260172","display_name":"British University in Dubai","ror":"https://ror.org/00mc18523","country_code":"AE","type":"education","lineage":["https://openalex.org/I193260172"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Khaled Shaalan","raw_affiliation_strings":["The British University in Dubai","The British Univ. in Dubai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The British University in Dubai","institution_ids":["https://openalex.org/I193260172"]},{"raw_affiliation_string":"The British Univ. in Dubai","institution_ids":["https://openalex.org/I193260172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060501075","display_name":"Hitham M. Abo Bakr","orcid":"https://orcid.org/0000-0002-0875-2202","observed_orcids":["https://orcid.org/0000-0002-0875-2202"]},"institutions":[{"id":"https://openalex.org/I192398990","display_name":"Zagazig University","ror":"https://ror.org/053g6we49","country_code":"EG","type":"education","lineage":["https://openalex.org/I192398990"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Hitham M. Abo Bakr","raw_affiliation_strings":["Zagazig University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zagazig University","institution_ids":["https://openalex.org/I192398990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112544984","display_name":"Ibrahim Ziedan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I192398990","display_name":"Zagazig University","ror":"https://ror.org/053g6we49","country_code":"EG","type":"education","lineage":["https://openalex.org/I192398990"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ibrahim Ziedan","raw_affiliation_strings":["Zagazig University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zagazig University","institution_ids":["https://openalex.org/I192398990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9385,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.73913345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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-diacritization","display_name":"Arabic diacritization","score":0.9800000190734863},{"id":"https://openalex.org/keywords/arabic-text-processing","display_name":"Arabic text processing","score":0.6000000238418579},{"id":"https://openalex.org/keywords/arabic-orthography","display_name":"Arabic orthography","score":0.5299999713897705},{"id":"https://openalex.org/keywords/case-endings","display_name":"case endings","score":0.44600000977516174},{"id":"https://openalex.org/keywords/arabic-vocabulary","display_name":"Arabic vocabulary","score":0.6389999985694885},{"id":"https://openalex.org/keywords/bigram-features","display_name":"bigram features","score":0.6610000133514404},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8560000061988831}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.847196638584137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8462353944778442},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8059837818145752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.728866696357727},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7283254265785217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6896247267723083},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5642154812812805},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4902496933937073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2687091827392578},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1621774.1621780","doi":"https://doi.org/10.3115/1621774.1621780","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621774.1621780","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621774.1621780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EACL 2009 Workshop on Computational Approaches to Semitic Languages - Semitic '09","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.9876","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.9876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/W/W09/W09-0804.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1621774.1621780","doi":"https://doi.org/10.3115/1621774.1621780","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621774.1621780","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621774.1621780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EACL 2009 Workshop on Computational Approaches to Semitic Languages - Semitic '09","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2065400286.pdf","grobid_xml":"https://content.openalex.org/works/W2065400286.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W45643337","https://openalex.org/W166521796","https://openalex.org/W1528620860","https://openalex.org/W1550053614","https://openalex.org/W1563088657","https://openalex.org/W1995945562","https://openalex.org/W2008056655","https://openalex.org/W2009639677","https://openalex.org/W2026897582","https://openalex.org/W2048978997","https://openalex.org/W2063116544","https://openalex.org/W2109613320","https://openalex.org/W2153186553","https://openalex.org/W2159859968","https://openalex.org/W2182012814","https://openalex.org/W2951299559","https://openalex.org/W4293077781","https://openalex.org/W6890406761"],"related_works":["https://openalex.org/W2899597854","https://openalex.org/W125610139","https://openalex.org/W7100572075","https://openalex.org/W4385846161","https://openalex.org/W3209410848","https://openalex.org/W2493183125","https://openalex.org/W2132283323","https://openalex.org/W6885024821","https://openalex.org/W1978716251","https://openalex.org/W2136534344"],"abstract_inverted_index":{"Modern":[0],"standard":[1],"Arabic":[2,14,33,55,65],"is":[3,83],"usually":[4],"written":[5],"without":[6],"diacritics.":[7,81],"This":[8],"makes":[9],"it":[10],"difficult":[11],"for":[12,74,121],"performing":[13],"text":[15,56,73],"processing.":[16],"Diacritization":[17],"helps":[18],"clarify":[19],"the":[20,37,48,113,123],"meaning":[21],"of":[22,50,70,109,112,125],"words":[23,34],"and":[24,67,102,117],"disambiguate":[25],"any":[26],"vague":[27],"spellings":[28],"or":[29],"pronunciations,":[30],"as":[31,85],"some":[32],"are":[35],"spelled":[36],"same":[38],"but":[39],"differ":[40],"in":[41,77],"meaning.":[42],"In":[43],"this":[44,126],"paper,":[45],"we":[46],"address":[47],"issue":[49],"adding":[51],"diacritics":[52],"to":[53,79],"undiacritized":[54],"using":[57,91],"a":[58,86],"hybrid":[59,95],"approach.":[60,127],"The":[61,94],"approach":[62,96,116],"requires":[63],"an":[64,110],"lexicon":[66,99],"large":[68],"corpus":[69],"fully":[71],"diacritized":[72],"training":[75],"purposes":[76],"order":[78],"detect":[80],"Case-Ending":[82],"treated":[84],"separate":[87],"post":[88],"processing":[89],"task":[90],"syntactic":[92],"information.":[93],"relies":[97],"on":[98],"retrieval,":[100],"bigram,":[101],"SVM-statistical":[103],"prioritized":[104],"techniques.":[105],"We":[106],"present":[107],"results":[108],"evaluation":[111],"proposed":[114],"diacritization":[115],"discuss":[118],"various":[119],"modifications":[120],"improving":[122],"performance":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}