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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/P19-2016.pdf