Combining Discrete Lexicon Probabilities with NMT for Low-Resource Mongolian-Chinese Translation

Abstract

Mongolian-Chinese neural machine translation (NMT) models often make mistakes in translating low-frequency words. We propose a method to alleviate this problem by improve NMT models with discrete translation lexicons that efficiently encode these low-frequency words. We describe a method to calcu-late the lexicon probability of generating the next word in the translation candi-date by using the attention vector of the NMT model to select which source word lexical probabilities the model should focus on. The method use this probabil-ity as a bias to combine with the stand-ard NMT probability. Experiments show an improvement of 4.02 BLEU score. We apply this method to large-scale corpus and improve the BLEU score. In addition, we also propose a novel approach to combine discrete probabilistic lexicons obtained from large-scale Mongolian - Chinese bilin-gual parallel corpus into NMT of small-scale corpus and enhance the perfor-mance of the system effectively.