Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise
Yatu Ji, Hongxu Hou, Chen Junjie, Nier Wu · 2019
For the translation of agglutinative language such as typical Mongolian, unknown (UN-K) 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 1 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.