{"id":"https://openalex.org/W2153186553","doi":"https://doi.org/10.3115/1220175.1220248","title":"Maximum entropy based restoration of Arabic diacritics","display_name":"Maximum entropy based restoration of Arabic diacritics","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2153186553","doi":"https://doi.org/10.3115/1220175.1220248","mag":"2153186553"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220248","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220248","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220248","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108365460","display_name":"Imed Zitouni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Imed Zitouni","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110191415","display_name":"Jeffrey Sorensen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Sorensen","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruhi Sarikaya","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108365460"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":8.8389,"has_fulltext":true,"cited_by_count":140,"citation_normalized_percentile":{"value":0.97662758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"584"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9969000220298767,"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/scripting-language","display_name":"Scripting language","score":0.7815371751785278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526931166648865},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6979771852493286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6184418201446533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5897952914237976},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.5407218337059021},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5375760197639465},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5182616710662842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5071470737457275},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.49639493227005005},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.49463316798210144},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.4353950619697571},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.20557048916816711},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1950257122516632},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.077477365732193}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7815371751785278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526931166648865},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6979771852493286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6184418201446533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5897952914237976},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.5407218337059021},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5375760197639465},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5182616710662842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5071470737457275},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.49639493227005005},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.49463316798210144},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.4353950619697571},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.20557048916816711},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1950257122516632},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.077477365732193},{"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:10.3115/1220175.1220248","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220248","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.6130","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.6130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1073.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220248","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220248","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2153186553.pdf","grobid_xml":"https://content.openalex.org/works/W2153186553.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1500614872","https://openalex.org/W1538879546","https://openalex.org/W1773803948","https://openalex.org/W1934019294","https://openalex.org/W1972583365","https://openalex.org/W1977830583","https://openalex.org/W2009639677","https://openalex.org/W2020079054","https://openalex.org/W2026897582","https://openalex.org/W2041349462","https://openalex.org/W2063116544","https://openalex.org/W2096175520","https://openalex.org/W2097341304","https://openalex.org/W2099942883","https://openalex.org/W2142340904","https://openalex.org/W2147880316","https://openalex.org/W2158195707","https://openalex.org/W2163306339","https://openalex.org/W4245136196"],"related_works":["https://openalex.org/W2740662036","https://openalex.org/W3142119062","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W131522978","https://openalex.org/W2250768577","https://openalex.org/W2160717663","https://openalex.org/W3173558315"],"abstract_inverted_index":{"Short":[0],"vowels":[1],"and":[2,18,21,68,88,127,150],"other":[3],"diacritics":[4,31,59],"are":[5,13],"not":[6],"part":[7],"of":[8,27,72,75,85,94,120,132,143,155],"written":[9],"Arabic":[10,110],"scripts.":[11],"Exceptions":[12],"made":[14],"for":[15,24,57],"important":[16],"political":[17],"religious":[19],"texts":[20],"in":[22,44,50,60],"scripts":[23],"beginning":[25],"students":[26],"Arabic.":[28],"Script":[29],"without":[30],"have":[32],"considerable":[33],"ambiguity":[34],"because":[35],"many":[36],"words":[37],"with":[38],"different":[39],"diacritic":[40,117,140],"patterns":[41],"appear":[42],"identical":[43],"a":[45,53,61,82,100,105,116,122,128,139,145,151],"diacritic-less":[46],"setting.":[47],"We":[48],"propose":[49,80],"this":[51],"paper":[52],"maximum":[54],"entropy":[55],"approach":[56,64],"restoring":[58],"document.":[62],"The":[63,92],"can":[65],"easily":[66],"integrate":[67],"make":[69],"effective":[70],"use":[71],"diverse":[73],"types":[74,97],"information;":[76],"the":[77],"model":[78],"we":[79,114,137],"integrates":[81],"wide":[83],"array":[84],"lexical,":[86],"segment-based":[87],"part-of-speech":[89],"tag":[90],"features.":[91],"combination":[93],"these":[95],"feature":[96],"leads":[98],"to":[99],"state-of-the-art":[101],"diacritization":[102],"model.":[103],"Using":[104],"publicly":[106],"available":[107],"corpus":[108],"(LDC's":[109],"Treebank":[111],"Part":[112],"3),":[113],"achieve":[115],"error":[118,124,130,141,147,153],"rate":[119,125,131,142,148,154],"5.1%,":[121],"segment":[123,146],"8.5%,":[126],"word":[129,152],"17.3%.":[133],"In":[134],"case-ending-less":[135],"setting,":[136],"obtain":[138],"2.2%,":[144],"4.0%,":[149],"7.2%.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}