Improving Neural Machine Translation with Offline Evaluations

Abstract

Reinforcement learning (RL) offers a principled framework for optimizing a given reward function and has been applied to a neural machine translation (NMT) problem to maximize arbitrary task metrics. However, previously adopted RL algorithms for NMT (e.g., policy gradient) are generally slow as they require online data collection, and limits the algorithm’s applicability to specific reward functions that can be evaluated online. In this paper, we present an offline RL algorithm called CER (conservative expectile regression). Despite the demanding nature of offline RL tasks, which are even more difficult with large models, this algorithm is capable to learn stably by explicitly exploiting the properties of NMT’s RL formulation, such as the deterministic transition function. We analyze and discuss the design choices of CER, and demonstrate in the experiments that the proposed method outperforms its competitors for offline reward optimization in NMT.