Neural Machine Translation with Adequacy-Oriented Learning

Authors

  • Xiang Kong Carnegie Mellon University
  • Zhaopeng Tu Tencent AI Lab
  • Shuming Shi Tencent AI Lab
  • Eduard Hovy Carnegie Mellon University
  • Tong Zhang Tencent AI Lab

DOI:

https://doi.org/10.1609/aaai.v33i01.33016618

Abstract

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation (MLE) cannot judge the real translation quality due to its several limitations. In this work, we propose an adequacyoriented learning mechanism for NMT by casting translation as a stochastic policy in Reinforcement Learning (RL), where the reward is estimated by explicitly measuring translation adequacy. Benefiting from the sequence-level training of RL strategy and a more accurate reward designed specifically for translation, our model outperforms multiple strong baselines, including (1) standard and coverage-augmented attention models with MLE-based training, and (2) advanced reinforcement and adversarial training strategies with rewards based on both word-level BLEU and character-level CHRF3. Quantitative and qualitative analyses on different language pairs and NMT architectures demonstrate the effectiveness and universality of the proposed approach.

Downloads

Published

2019-07-17

How to Cite

Kong, X., Tu, Z., Shi, S., Hovy, E., & Zhang, T. (2019). Neural Machine Translation with Adequacy-Oriented Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6618-6625. https://doi.org/10.1609/aaai.v33i01.33016618

Issue

Section

AAAI Technical Track: Natural Language Processing