DeepAI AI Chat
Log In Sign Up

Data-Driven Adaptive Simultaneous Machine Translation

by   Guangxu Xun, et al.
Baidu, Inc.

In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is a fixed policy that can not adaptively adjust latency given context, and (b) its training is much slower than full-sentence translation. To alleviate these issues, we propose a novel and efficient training scheme for adaptive SimulMT by augmenting the training corpus with adaptive prefix-to-prefix pairs, while the training complexity remains the same as that of training full-sentence translation models. Experiments on two language pairs show that our method outperforms all strong baselines in terms of translation quality and latency.


page 1

page 2

page 3

page 4


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

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

Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy

Simultaneous machine translation (SiMT) generates translation before rea...

Stream-level Latency Evaluation for Simultaneous Machine Translation

Simultaneous machine translation has recently gained traction thanks to ...

LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation

Simultaneous machine translation, which aims at a real-time translation,...

Simultaneous Translation Policies: From Fixed to Adaptive

Adaptive policies are better than fixed policies for simultaneous transl...

Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy

Simultaneous translation, which starts translating each sentence after r...

Learning Coupled Policies for Simultaneous Machine Translation

In simultaneous machine translation, the system needs to incrementally g...