Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang · 2019
Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP.Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning.We propose a much simpler single model that adds a "delay" token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training.Experiments on Chinese↔English simultaneous translation show that our work leads to flexible policies that achieve better BLEU scores and lower latencies compared to both fixed and RL-learned policies.