Sequence-to-sequence neural network models for transliteration
Abstract
Transliteration is a key component of machine translation systems and software internationalization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing datasets. In an effort to make machine transliteration accessible, we open source a new Arabic to English transliteration dataset and our trained models.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2016
- DOI:
- 10.48550/arXiv.1610.09565
- arXiv:
- arXiv:1610.09565
- Bibcode:
- 2016arXiv161009565R
- Keywords:
-
- Computer Science - Computation and Language