Log In Sign Up

Simultaneous Translation Policies: From Fixed to Adaptive

by   Baigong Zheng, et al.

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.


page 1

page 2

page 3

page 4


Simultaneous Translation with Flexible Policy via Restricted Imitation Learning

Simultaneous translation is widely useful but remains one of the most di...

STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency

Simultaneous translation, which translates sentences before they are fin...

Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation

Simultaneous translation is widely useful but remains challenging. Previ...

Data-Driven Adaptive Simultaneous Machine Translation

In simultaneous translation (SimulMT), the most widely used strategy is ...

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation

Simultaneous machine translation (SiMT) starts its translation before re...

Anticipation-free Training for Simultaneous Translation

Simultaneous translation (SimulMT) speeds up the translation process by ...

Improving Simultaneous Translation with Pseudo References

Simultaneous translation is vastly different from full-sentence translat...