{"id":"https://openalex.org/W2543137198","doi":"https://doi.org/10.1109/icta.2015.7426904","title":"Evaluation of the ambiguity caused by the absence of diacritical marks in Arabic texts: Statistical study","display_name":"Evaluation of the ambiguity caused by the absence of diacritical marks in Arabic texts: Statistical study","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2543137198","doi":"https://doi.org/10.1109/icta.2015.7426904","mag":"2543137198"},"language":"en","primary_location":{"id":"doi:10.1109/icta.2015.7426904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta.2015.7426904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 5th International Conference on Information &amp; Communication Technology and Accessibility (ICTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011278582","display_name":"Mohamed Boudchiche","orcid":"https://orcid.org/0000-0002-8287-5665"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Mohamed Boudchiche","raw_affiliation_strings":["Department of Mathematics and Computer Science, University Mohamed first, Oujda, Morocco"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University Mohamed first, Oujda, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040301937","display_name":"Azzeddine Mazroui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Azzeddine Mazroui","raw_affiliation_strings":["Department of Mathematics and Computer Science, University Mohamed first, Oujda, Morocco"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University Mohamed first, Oujda, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011278582"],"corresponding_institution_ids":["https://openalex.org/I4210108110"],"apc_list":null,"apc_paid":null,"fwci":3.5611,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93943242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9988999962806702,"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":0.9969000220298767,"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/ambiguity","display_name":"Ambiguity","score":0.8387244939804077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7025850415229797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6550248861312866},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.6386937499046326},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6201881170272827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5464531183242798},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.4954296350479126},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4868590235710144},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.45826536417007446},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4330664277076721},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4188055396080017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18981075286865234},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15302571654319763}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8387244939804077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7025850415229797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6550248861312866},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.6386937499046326},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6201881170272827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464531183242798},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.4954296350479126},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4868590235710144},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.45826536417007446},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4330664277076721},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4188055396080017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18981075286865234},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15302571654319763},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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:10.1109/icta.2015.7426904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta.2015.7426904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 5th International Conference on Information &amp; Communication Technology and Accessibility (ICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W195605629","https://openalex.org/W1562769351","https://openalex.org/W1984708705","https://openalex.org/W1989326298","https://openalex.org/W2005615872","https://openalex.org/W2063116544","https://openalex.org/W2066553852","https://openalex.org/W2103667219","https://openalex.org/W2208839653","https://openalex.org/W2326206218","https://openalex.org/W6633584078","https://openalex.org/W7032917496"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W3006682748","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W1097487277","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2768610039"],"abstract_inverted_index":{"This":[0],"work":[1],"falls":[2],"within":[3],"the":[4,7,16,22,31,46,48,50,53,57,82,91,95,99,112,120],"framework":[5],"of":[6,18,24,56,84,94,114],"Natural":[8],"Language":[9],"Processing.":[10],"Its":[11],"objective":[12],"is":[13],"to":[14],"assess":[15],"level":[17],"ambiguity":[19,96],"caused":[20],"by":[21],"absence":[23,83],"diacritical":[25,85],"marks":[26,86],"in":[27,87,98],"Arabic":[28,88],"texts":[29,89],"during":[30],"information":[32,100],"extraction":[33,101],"process.":[34,102],"We":[35],"have":[36],"carried":[37],"out":[38],"a":[39,63,115],"statistical":[40],"study":[41,79,107],"based":[42,104],"on":[43,105],"four":[44],"indicators:":[45],"root,":[47],"lemma,":[49],"stem":[51],"and":[52],"POS":[54],"tag":[55],"word.":[58],"For":[59],"this,":[60],"we":[61,108],"used":[62],"large":[64],"vowelized":[65,116],"corpus":[66,117],"containing":[67],"more":[68],"than":[69],"80":[70],"million":[71],"words":[72],"collected":[73],"from":[74],"several":[75],"sources.":[76],"The":[77],"conducted":[78],"showed":[80],"that":[81,111],"represents":[90],"main":[92],"cause":[93],"observed":[97],"Thus,":[103],"this":[106],"can":[109],"conclude":[110],"use":[113],"reduces":[118],"considerably":[119],"ambiguity.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}
