Opportunistic Decoding with Timely Correction for Simultaneous Translation
This addresses the problem of balancing quality and latency for real-time translation users, representing a strong incremental improvement over existing methods.
The paper tackles the trade-off between translation quality and latency in simultaneous translation by proposing an opportunistic decoding technique with timely correction, which reduces latency and increases BLEU by up to +3.1 points while keeping revision rates under 8%.
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.