DeepAI AI Chat
Log In Sign Up

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

by   Shoutao Guo, et al.

Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adaptive policy achieves better latency-quality tradeoffs by adopting a flexible translation policy. If the policy can evaluate rationality before taking action, the probability of incorrect actions will also decrease. However, previous methods lack evaluation of actions before taking them. In this paper, we propose a method of performing the adaptive policy via integrating post-evaluation into the fixed policy. Specifically, whenever a candidate token is generated, our model will evaluate the rationality of the next action by measuring the change in the source content. Our model will then take different actions based on the evaluation results. Experiments on three translation tasks show that our method can exceed strong baselines under all latency.


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

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

Data-Driven Adaptive Simultaneous Machine Translation

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

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search

Simultaneous machine translation (SiMT) starts to output translation whi...

Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework

Simultaneous machine translation (SiMT) starts translating while receivi...

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

A common assumption when training embodied agents is that the impact of ...

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...