{"title":"ARABIC TEXT","authors":"Kareem Darwish","doi":"10.2307/j.ctv1b9f5x9.8","DOIUrl":"https://doi.org/10.2307/j.ctv1b9f5x9.8","url":null,"abstract":"Title of Dissertation: Probabilistic Methods for Searching OCR-Degrad ed Arabic Text Kareem Darwish, Doctor of Philosophy, 2003 Dissertation directed by: Dr. Bruce Jacob Department of Electrical and Computer Engineering Dr. Douglas W. Oard College of Information Studies Since many Arabic documents are available only in print, automating retri eval from collections of scanned Arabic document images using Optical Character Recogni tion (OCR) is an important problem. This dissertation addresses retrieval of Ara bic document images based on OCR, with emphasis on probabilistic methods to improve retrieval effectiveness. Arabic’s rich morphology (word construction) and complex orthograph y (writing system) present unique challenges for OCR and Information Ret rieval (IR) systems. New probabilistic structured query methods that leverage replacement probabi lities were developed in this research to improve retrieval effectiveness in OCR degraded te xt retrieval and their generality has been shown in cross-language inform ati n retrieval. For the OCR-degraded text retrieval, the probabilistic structured query methods w ere applied using the most effective index terms for OCR-degraded text, with replacement probabilities estimated using an OCR degradation model. Overlapping character n-grams and combinations of character n-grams with terms obtained through morphological analysis were found to be the most effective indexing terms for Arabic colle ti ns of varying sizes, genres, and degradation levels. For index terms requiring morphol ogical analysis, existing automated Arabic morphological analysis techniques wer adapted to make them more suitable for IR applications. Different OCR models were devel op d to account for the complex Arabic orthography and a group of tests were crafted to veri fy that modeled and real OCR degradation have similar effects on IR. One of the models was also used to synthetically degrade a large document collection. The techniques presented in this dissertation offer the potential to unlock access t o printed documents of Arabic and other languages with similar orthographic characteristics. PROBABILISTIC METHODS FOR SEARCHING OCR-DEGRADED ARABIC TEXT","PeriodicalId":323953,"journal":{"name":"The Continuatio of the Samaritan Chronicle_x000B_of Abu l-Fath al-Samiri al-Danafi","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125469546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"GEOGRAPHICAL APPENDIX","authors":"","doi":"10.2307/j.ctv1b9f5x9.9","DOIUrl":"https://doi.org/10.2307/j.ctv1b9f5x9.9","url":null,"abstract":"","PeriodicalId":323953,"journal":{"name":"The Continuatio of the Samaritan Chronicle_x000B_of Abu l-Fath al-Samiri al-Danafi","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131603532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}