{"id":"https://openalex.org/W2152974942","doi":"https://doi.org/10.1109/icdar.2015.7333846","title":"Hybrid word/Part-of-Arabic-Word Language Models for arabic text document recognition","display_name":"Hybrid word/Part-of-Arabic-Word Language Models for arabic text document recognition","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2152974942","doi":"https://doi.org/10.1109/icdar.2015.7333846","mag":"2152974942"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2015.7333846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","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/A5108375234","display_name":"Mohamed Faouzi BenZeghiba","orcid":null},"institutions":[{"id":"https://openalex.org/I35298706","display_name":"ESIEA University","ror":"https://ror.org/00g6cx256","country_code":"FR","type":"education","lineage":["https://openalex.org/I35298706"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mohamed Faouzi BenZeghiba","raw_affiliation_strings":["A2iA S.A, Paris, France"],"affiliations":[{"raw_affiliation_string":"A2iA S.A, Paris, France","institution_ids":["https://openalex.org/I35298706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040476308","display_name":"J\u00e9r\u00f4me Louradour","orcid":null},"institutions":[{"id":"https://openalex.org/I35298706","display_name":"ESIEA University","ror":"https://ror.org/00g6cx256","country_code":"FR","type":"education","lineage":["https://openalex.org/I35298706"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jerome Louradour","raw_affiliation_strings":["A2iA S.A, Paris, France"],"affiliations":[{"raw_affiliation_string":"A2iA S.A, Paris, France","institution_ids":["https://openalex.org/I35298706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024834377","display_name":"Christopher Kermorvant","orcid":"https://orcid.org/0000-0002-7508-4080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Kermorvant","raw_affiliation_strings":["Teklia S.A.S, Paris, France"],"affiliations":[{"raw_affiliation_string":"Teklia S.A.S, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108375234"],"corresponding_institution_ids":["https://openalex.org/I35298706"],"apc_list":null,"apc_paid":null,"fwci":2.1572,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90202638,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8148336410522461},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7585456967353821},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.669200599193573},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6356662511825562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6242803335189819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880112648010254},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5705474615097046},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5257112383842468},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5238314270973206},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4726252555847168},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4609428644180298},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.4407367706298828},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1957537829875946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148336410522461},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7585456967353821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.669200599193573},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6356662511825562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6242803335189819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880112648010254},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5705474615097046},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5257112383842468},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5238314270973206},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4726252555847168},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4609428644180298},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.4407367706298828},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1957537829875946},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2015.7333846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1534448508","https://openalex.org/W1844448538","https://openalex.org/W1993312227","https://openalex.org/W1994420166","https://openalex.org/W2004220942","https://openalex.org/W2017718251","https://openalex.org/W2024870788","https://openalex.org/W2069617593","https://openalex.org/W2103744051","https://openalex.org/W2109813301","https://openalex.org/W2123191374","https://openalex.org/W2147272182","https://openalex.org/W2163605009","https://openalex.org/W2170942820","https://openalex.org/W2884796895","https://openalex.org/W2964325005","https://openalex.org/W3146209407","https://openalex.org/W4211260480","https://openalex.org/W6631362777","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W4390986482","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,22,42,51],"simple":[4],"approach":[5],"to":[6,40,49],"generate":[7,41],"an":[8],"efficient":[9],"hybrid":[10,43,52,86,125,144],"word/Part-of-Arabic-Word":[11],"(PAW)":[12],"Language":[13],"Model":[14],"(LM).":[15],"More":[16],"precisely,":[17],"less":[18,147],"frequent":[19,38],"words":[20,39],"in":[21,109],"full":[23,64,84,89,120,152],"word":[24,69,112,139],"vocabulary":[25,45,70],"are":[26,33,71,94],"decomposed":[27],"into":[28],"PAWs.":[29],"The":[30],"resulted":[31],"PAWs":[32],"incorporated":[34],"with":[35,63],"the":[36,68,75,78,119,123,129],"most":[37],"word-PAW":[44],"which":[46],"is":[47],"used":[48],"estimate":[50],"flat":[53],"n-gram":[54],"statistical":[55],"language":[56,61],"model.":[57],"For":[58],"comparison":[59],"purposes,":[60],"models":[62],"PAW":[65,90,121,153],"decomposition":[66],"of":[67,77,81,111,133],"generated.":[72],"To":[73],"assess":[74],"quality":[76],"three":[79,97],"types":[80],"LMs":[82,126,145],"(i.e.":[83],"word,":[85],"word/PAW":[87],"and":[88,106,122,131],"LMs),":[91],"evaluation":[92],"experiments":[93],"conducted":[95],"under":[96],"different":[98],"tasks":[99],"using":[100,118,138,143,151],"two":[101],"benchmarking":[102],"databases,":[103],"namely":[104],"Maurdor":[105],"Khatt.":[107],"Results":[108],"terms":[110],"error":[113],"rate":[114],"show":[115],"that":[116],"systems":[117,137,142],"proposed":[124],"perform":[127],"equally":[128],"same,":[130],"both":[132],"them,":[134],"systematically,":[135],"outperform":[136],"LMs.":[140,154],"However,":[141],"require":[146],"memory":[148],"than":[149],"those":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}