Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise

Yatu Ji, Hongxu Hou, Chen Junjie, Nier Wu


Abstract
For the translation of agglutinative language such as typical Mongolian, unknown (UNK) words not only come from the quite restricted vocabulary, but also mostly from misunderstanding of the translation model to the morphological changes. In this study, we introduce a new adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation. The training process can be described as three adversarial sub models (generator, value screener and discriminator), playing a win-win game. In this game, the added screener plays the role of emphasizing that the discriminator pays attention to the added Mongolian morphological noise in the form of pseudo-data and improving the training efficiency. The experimental results show that the newly emerged Mongolian-Chinese task is state-of-the-art. Under this premise, the training time is greatly shortened.
Anthology ID:
P19-2016
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Fernando Alva-Manchego, Eunsol Choi, Daniel Khashabi
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
123–129
Language:
URL:
https://aclanthology.org/P19-2016
DOI:
10.18653/v1/P19-2016
Bibkey:
Cite (ACL):
Yatu Ji, Hongxu Hou, Chen Junjie, and Nier Wu. 2019. Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 123–129, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise (Ji et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-2016.pdf