{"id":"https://openalex.org/W2970568224","doi":"https://doi.org/10.18653/v1/w19-4606","title":"Homograph Disambiguation through Selective Diacritic Restoration","display_name":"Homograph Disambiguation through Selective Diacritic Restoration","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970568224","doi":"https://doi.org/10.18653/v1/w19-4606","mag":"2970568224"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4606","pdf_url":null,"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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w19-4606","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051917159","display_name":"Sawsan Alqahtani","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]},{"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":["SA","US"],"is_corresponding":true,"raw_author_name":"Sawsan Alqahtani","raw_affiliation_strings":["The George Washington University","Princess Nourah Bint Abdul Rahman University"],"affiliations":[{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Princess Nourah Bint Abdul Rahman University","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002602581","display_name":"Hanan Aldarmaki","orcid":"https://orcid.org/0000-0003-1706-1777"},"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":"Hanan Aldarmaki","raw_affiliation_strings":["The George Washington University"],"affiliations":[{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"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":["AWS, Amazon AI","The George Washington University"],"affiliations":[{"raw_affiliation_string":"AWS, Amazon AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051917159"],"corresponding_institution_ids":["https://openalex.org/I106778892","https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":1.302,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85743521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"59"},"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":0.9987000226974487,"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":0.8157056570053101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7032973766326904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6729093790054321},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5609877109527588},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4915834367275238},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.426100492477417},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.42513179779052734},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.4243796169757843},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18165215849876404},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08911335468292236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157056570053101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7032973766326904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6729093790054321},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5609877109527588},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4915834367275238},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.426100492477417},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.42513179779052734},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.4243796169757843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18165215849876404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08911335468292236},{"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:10.18653/v1/w19-4606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4606","pdf_url":null,"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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.04479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.04479","pdf_url":"https://arxiv.org/pdf/1912.04479","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4606","pdf_url":null,"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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W125610139","https://openalex.org/W1515242458","https://openalex.org/W1522263329","https://openalex.org/W1614298861","https://openalex.org/W1987302197","https://openalex.org/W2006969979","https://openalex.org/W2011402185","https://openalex.org/W2015930392","https://openalex.org/W2017991382","https://openalex.org/W2049633694","https://openalex.org/W2101105183","https://openalex.org/W2108997961","https://openalex.org/W2116702211","https://openalex.org/W2121227244","https://openalex.org/W2133564696","https://openalex.org/W2135875128","https://openalex.org/W2144600658","https://openalex.org/W2145262681","https://openalex.org/W2148708890","https://openalex.org/W2156202195","https://openalex.org/W2157835502","https://openalex.org/W2161160262","https://openalex.org/W2184135559","https://openalex.org/W2250234233","https://openalex.org/W2250816155","https://openalex.org/W2251212642","https://openalex.org/W2296039906","https://openalex.org/W2493916176","https://openalex.org/W2497040301","https://openalex.org/W2571755499","https://openalex.org/W2576709312","https://openalex.org/W2579343286","https://openalex.org/W2739664078","https://openalex.org/W2767595811","https://openalex.org/W2775425324","https://openalex.org/W2787700961","https://openalex.org/W2798935874","https://openalex.org/W2950577311","https://openalex.org/W2951990284","https://openalex.org/W2963212250","https://openalex.org/W2963940534","https://openalex.org/W2964308564","https://openalex.org/W3104033643","https://openalex.org/W3202110839","https://openalex.org/W3210631460","https://openalex.org/W4200593948","https://openalex.org/W4313908941"],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W2371976984","https://openalex.org/W1555832326","https://openalex.org/W2352160949","https://openalex.org/W4298186509","https://openalex.org/W2556702969"],"abstract_inverted_index":{"Lexical":[0],"ambiguity,":[1],"a":[2,75,142],"challenging":[3],"phenomenon":[4],"in":[5,21,32,52,56,63,148],"all":[6],"natural":[7],"languages,":[8],"is":[9],"particularly":[10],"prevalent":[11],"for":[12,72,79],"languages":[13],"with":[14,39],"diacritics":[15,27],"that":[16,100],"tend":[17],"to":[18,29,60,84,89,141],"be":[19],"omitted":[20],"writing,":[22],"such":[23],"as":[24],"Arabic.":[25],"Omitting":[26],"leads":[28,59,83],"an":[30],"increase":[31,55],"the":[33,40,54,108],"number":[34],"of":[35,77],"homographs:":[36],"different":[37],"words":[38,78],"same":[41],"spelling.":[42],"Diacritic":[43],"restoration":[44],"could":[45],"theoretically":[46],"help":[47],"disambiguate":[48],"these":[49,95],"words,":[50],"but":[51],"practice,":[53],"overall":[57],"sparsity":[58,102],"performance":[61,147],"degradation":[62],"NLP":[64],"applications.":[65,150],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"approaches":[71,96],"automatically":[73],"marking":[74],"subset":[76],"diacritic":[80,93],"restoration,":[81,94],"which":[82],"selective":[85,138],"homograph":[86],"disambiguation.":[87,105],"Compared":[88],"full":[90],"or":[91],"no":[92],"yield":[97],"selectively-diacritized":[98],"datasets":[99],"balance":[101],"and":[103,122,145],"lexical":[104],"We":[106],"evaluate":[107],"various":[109],"selection":[110],"strategies":[111,136],"extrinsically":[112],"on":[113,128,137],"several":[114],"downstream":[115,149],"applications:":[116],"neural":[117],"machine":[118],"translation,":[119],"part-of-speech":[120],"tagging,":[121],"semantic":[123],"textual":[124],"similarity.":[125],"Our":[126],"experiments":[127],"Arabic":[129],"show":[130],"promising":[131],"results,":[132],"where":[133],"our":[134],"devised":[135],"diacritization":[139],"lead":[140],"more":[143],"balanced":[144],"consistent":[146]},"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":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}