Arabic OCR Error Correction Using Character Segment Correction, Language Modeling, and Shallow Morphology

@inproceedings{magdy-darwish:2006:EMNLP, abstract = {This paper explores the use of a character segment based character correction model, language modeling, and shallow morphology for Arabic OCR error correction. Experimentation shows that character segment based correction is superior to single character correction and that language modeling boosts correction, by improving the ranking of candidate corrections, while shallow morphology had a small adverse effect. Further, given sufficiently large corpus to extract a dictionary and to train a language model, word based correction works well for a morphologically rich language such as Arabic.}, address = {Sydney, Australia}, author = {Magdy, Walid and Darwish, Kareem }, booktitle = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing}, citeulike-article-id = {1704995}, keywords = {arabic, arabic\_ocr, for\_gabe, language\_models, morphology, ocr}, pages = {408--414}, posted-at = {2007-09-28 14:06:39}, priority = {0}, publisher = {Association for Computational Linguistics}, title = {Arabic OCR Error Correction Using Character Segment Correction, Language Modeling, and Shallow Morphology}, url = {http://www.aclweb.org/anthology/W/W06/W06-1648}, year = {2006} }

TY - CONF ID - magdy-darwish:2006:EMNLP L3 - citeulike-article-id:1704995 TI - Arabic OCR Error Correction Using Character Segment Correction, Language Modeling, and Shallow Morphology T2 - Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing SP - 408 EP - 414 AD - Sydney, Australia PB - Association for Computational Linguistics N2 - This paper explores the use of a character segment based character correction model, language modeling, and shallow morphology for Arabic OCR error correction. Experimentation shows that character segment based correction is superior to single character correction and that language modeling boosts correction, by improving the ranking of candidate corrections, while shallow morphology had a small adverse effect. Further, given sufficiently large corpus to extract a dictionary and to train a language model, word based correction works well for a morphologically rich language such as Arabic. KW - arabic KW - arabic_ocr KW - for_gabe KW - language_models KW - morphology KW - ocr AU - Magdy, Walid AU - Darwish, Kareem PY - 2006/// UR - http://www.aclweb.org/anthology/W/W06/W06-1648 ER -