Opportunistic Decoding with Timely Correction for Simultaneous Translation

TL;DR

This paper introduces an opportunistic decoding method for simultaneous translation that balances low latency with high translation quality by over-generating and timely correcting words, significantly improving BLEU scores.

Contribution

The paper proposes a novel opportunistic decoding approach with timely correction, enhancing translation quality and reducing latency in simultaneous translation.

Findings

Reduced latency significantly

Achieved up to +3.1 BLEU score increase

Maintained revision rate under 8%

Abstract

Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and latency, i.e., the decoding policy is usually either too aggressive or too conservative. We propose an opportunistic decoding technique with timely correction ability, which always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information. At the same time, it also corrects, in a timely fashion, the mistakes in the former overgenerated words when observing more source context to ensure high translation quality. Experiments show our technique achieves substantial reduction in latency and up to +3.1 increase in BLEU, with revision rate under 8% in Chinese-to-English and English-to-Chinese translation.