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

TL;DR

This paper introduces a universal simultaneous machine translation model using a mixture-of-experts approach, enabling high-quality translation across various latency levels with a single trained model.

Contribution

The proposed Mixture-of-Experts Wait-k Policy allows a single model to adapt to different latency requirements, reducing computational costs compared to multiple models.

Findings

Outperforms strong baselines across multiple latency levels

Achieves state-of-the-art results with adaptive policy

Demonstrates flexibility and efficiency in real-world scenarios

Abstract

Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency. To fulfill the requirements of different translation quality and latency in practical applications, the previous methods usually need to train multiple SiMT models for different latency levels, resulting in large computational costs. In this paper, we propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency with only one trained model. Specifically, our method employs multi-head attention to accomplish the mixture of experts where each head is treated as a wait-k expert with its own waiting words number, and given a test latency and source inputs, the weights of the experts are accordingly adjusted to produce the best translation. Experiments on three datasets show that our method outperforms all the strong baselines under different latency, including the state-of-the-art adaptive policy.