Life Is Short, Train It Less: Neural Machine Tibetan-Chinese Translation Based on mRASP and Dataset Enhancement

Hao Wang, Yongbin Yu, Tashi Nyima, Rinchen Dongrub, Favour Ekong, Mengwei Ai, Kalzang Gyatso, Yong Cuo, Qun Nuo

Abstract: This paper highlights a multilingual pre-trained neural machine translation architecture as well as a dataset augmentation approach based on curvature selection. The multilingual pre-trained model is designed to increase the performance of machine translation with low resources by bringing in more common information. Instead of repeatedly training several checkpoints from scratch, this study proposes a checkpoint selection strategy that uses a cleaned optimizer to hijack a midway status. Experiments with our own dataset on the Chinese-Tibetan translation demonstrate that our architecture gets a 32.65 BLEU score, while in the reverse direction, it obtains a 39.51 BLEU score. This strategy drastically reduces the amount of time spent training. To demonstrate the validity of our method, this paper shows a visualization of curvature for a real-world training scenario.