{"id":"https://openalex.org/W2250751111","doi":"https://doi.org/10.18653/v1/d15-1274","title":"Arabic Diacritization with Recurrent Neural Networks","display_name":"Arabic Diacritization with Recurrent Neural Networks","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250751111","doi":"https://doi.org/10.18653/v1/d15-1274","mag":"2250751111"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1274","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1274","pdf_url":"https://www.aclweb.org/anthology/D15-1274.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 2015 Conference on Empirical Methods in 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/D15-1274.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2281","last_page":"2285"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","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":0.8392330408096313},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6856849789619446},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6589768528938293},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6493095755577087},{"id":"https://openalex.org/keywords/hebrew","display_name":"Hebrew","score":0.6204031109809875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6200039386749268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6018529534339905},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5798937082290649},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5626236200332642},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4950522482395172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43521034717559814},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2244926393032074},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15386465191841125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392330408096313},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6856849789619446},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6589768528938293},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6493095755577087},{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.6204031109809875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6200039386749268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018529534339905},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5798937082290649},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5626236200332642},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4950522482395172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43521034717559814},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2244926393032074},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15386465191841125},{"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/d15-1274","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1274","pdf_url":"https://www.aclweb.org/anthology/D15-1274.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.3183","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.3183","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/D/D15/D15-1274.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1274","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1274","pdf_url":"https://www.aclweb.org/anthology/D15-1274.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250751111.pdf","grobid_xml":"https://content.openalex.org/works/W2250751111.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W201141796","https://openalex.org/W304834817","https://openalex.org/W1614298861","https://openalex.org/W2056382745","https://openalex.org/W2064675550","https://openalex.org/W2109613320","https://openalex.org/W2136534344","https://openalex.org/W2143612262","https://openalex.org/W2153186553","https://openalex.org/W2153579005","https://openalex.org/W2251265054","https://openalex.org/W2296039906","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W1558215493","https://openalex.org/W1976009970","https://openalex.org/W2084800428","https://openalex.org/W2923538289","https://openalex.org/W2891418498","https://openalex.org/W2807934979","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"Arabic,":[0],"Hebrew,":[1],"and":[2,13,48,57],"similar":[3],"languages":[4],"are":[5],"typically":[6,40],"written":[7],"without":[8,85],"diacritics,":[9],"leading":[10],"to":[11,28,54,103],"ambiguity":[12],"posing":[14],"a":[15,32,61],"major":[16],"challenge":[17],"for":[18,70],"core":[19],"language":[20],"processing":[21],"tasks":[22],"like":[23,45],"speech":[24],"recognition.":[25],"Previous":[26],"approaches":[27],"automatic":[29],"diacritization":[30],"employed":[31],"variety":[33],"of":[34],"machine":[35],"learning":[36],"techniques.":[37],"However,":[38],"they":[39],"rely":[41],"on":[42,87],"existing":[43],"tools":[44],"morphological":[46],"analyzers":[47],"therefore":[49],"cannot":[50],"be":[51],"easily":[52],"extended":[53],"new":[55],"genres":[56],"languages.":[58],"We":[59,90],"develop":[60],"recurrent":[62],"neural":[63],"network":[64],"with":[65],"long":[66],"shortterm":[67],"memory":[68],"layers":[69],"predicting":[71],"diacritics":[72],"in":[73],"Arabic":[74],"text.":[75],"Our":[76],"language-independent":[77],"approach":[78],"is":[79],"trained":[80],"solely":[81],"from":[82],"diacritized":[83],"text":[84],"relying":[86],"external":[88],"tools.":[89],"show":[91],"experimentally":[92],"that":[93,100],"our":[94],"model":[95],"can":[96],"rival":[97],"state-of-the-art":[98],"methods":[99],"have":[101],"access":[102],"additional":[104],"resources.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}