@inproceedings{a6304b1e23424c8cb945e729b8113411,
title = "Reranking with linguistic and semantic features for arabic optical character recognition",
abstract = "Optical Character Recognition (OCR) systems for Arabic rely on information contained in the scanned images to recognize sequences of characters and on language models to emphasize fluency. In this paper we incorporate linguistically and seman-tically motivated features to an existing OCR system. To do so we follow an n-best list reranking approach that exploits recent advances in learning to rank techniques. We achieve 10.1% and 11.4% reduction in recognition word error rate (WER) relative to a standard baseline system on typewritten and handwritten Arabic respectively.",
author = "Nadi Tomeh and Nizar Habash and Ryan Roth and Noura Farra and Pradeep Dasigi and Mona Diab",
year = "2013",
language = "English (US)",
isbn = "9781937284510",
series = "ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "549--555",
booktitle = "Short Papers",
note = "51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 ; Conference date: 04-08-2013 Through 09-08-2013",
}