Simultaneous Translation Policies: From Fixed to Adaptive
share
Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform the simple fixed policies. We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies. Experiments on Chinese->English and German->English show that our adaptive policies can outperform the fixed policies by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses greedy full-sentence translation in BLEU scores, but with much lower latency.
READ FULL TEXT