Comparison of Assorted Models for Transliteration
Saeed Najafi, Bradley Hauer, Rashed Rubby Riyadh, Leyuan Yu, Grzegorz Kondrak
Abstract
We report the results of our experiments in the context of the NEWS 2018 Shared Task on Transliteration. We focus on the comparison of several diverse systems, including three neural MT models. A combination of discriminative, generative, and neural models obtains the best results on the development sets. We also put forward ideas for improving the shared task.- Anthology ID:
- W18-2412
- Volume:
- Proceedings of the Seventh Named Entities Workshop
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Nancy Chen, Rafael E. Banchs, Xiangyu Duan, Min Zhang, Haizhou Li
- Venue:
- NEWS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 84–88
- Language:
- URL:
- https://aclanthology.org/W18-2412
- DOI:
- 10.18653/v1/W18-2412
- Cite (ACL):
- Saeed Najafi, Bradley Hauer, Rashed Rubby Riyadh, Leyuan Yu, and Grzegorz Kondrak. 2018. Comparison of Assorted Models for Transliteration. In Proceedings of the Seventh Named Entities Workshop, pages 84–88, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Comparison of Assorted Models for Transliteration (Najafi et al., NEWS 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W18-2412.pdf