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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/W18-2412.pdf