Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
This work addresses the challenge of real-time translation for live and streaming applications, representing an incremental improvement over prior scheduling methods.
The paper tackles the problem of balancing translation quality and latency in simultaneous machine translation by introducing Monotonic Infinite Lookback (MILk) attention, which learns an adaptive schedule jointly with the translation model, achieving favorable latency-quality trade-offs compared to existing strategies like wait-k for many latency values.
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simultaneous systems must carefully schedule their reading of the source sentence to balance quality against latency. We present the first simultaneous translation system to learn an adaptive schedule jointly with a neural machine translation (NMT) model that attends over all source tokens read thus far. We do so by introducing Monotonic Infinite Lookback (MILk) attention, which maintains both a hard, monotonic attention head to schedule the reading of the source sentence, and a soft attention head that extends from the monotonic head back to the beginning of the source. We show that MILk's adaptive schedule allows it to arrive at latency-quality trade-offs that are favorable to those of a recently proposed wait-k strategy for many latency values.