STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
This addresses the problem of real-time translation for applications like live captioning, though it is an incremental improvement over existing methods.
The paper tackles simultaneous translation by proposing a prefix-to-prefix framework that implicitly learns anticipation, using a wait-k policy to generate translations k words behind the source, achieving low latency and reasonable quality compared to full-sentence translation on four language directions.
Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very simple yet surprisingly effective wait-k policy trained to generate the target sentence concurrently with the source sentence, but always k words behind. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: zh<->en and de<->en.