Automated Prediction of Medieval Arabic Diacritics

Automated Prediction of Medieval Arabic Diacritics

This study uses a character level neural machine translation approach trained on a long short-term memory-based bi-directional recurrent neural network architecture for diacritization of Medieval Arabic. The results improve from the online tool used as a baseline. A diacritization model have been pu...

Full description

Saved in:
Bibliographic Details
Main Authors: Alnajjar, Khalid, Hämäläinen, Mika, Partanen, Niko, Rueter, Jack
Format: Journal Article
Language:English
Published: 11-10-2020
Subjects:
Computer Science - Computation and Language
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study uses a character level neural machine translation approach trained on a long short-term memory-based bi-directional recurrent neural network architecture for diacritization of Medieval Arabic. The results improve from the online tool used as a baseline. A diacritization model have been published openly through an easy to use Python package available on PyPi and Zenodo. We have found that context size should be considered when optimizing a feasible prediction model.
DOI:10.48550/arxiv.2010.05269