STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency
Authors:
- Controllable LatencyCLControllable Latency
- Mingbo MaMMMingbo Ma
- Liang HuangLHLiang Huang
- Hao XiongHXHao Xiong
- Chuanqiang ZhangCZChuanqiang Zhang
- Zhongjun HeZHZhongjun He
Preprint
Abstract
Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences and simultaneity requirements. We introduce a very simple yet surprisingly effective `wait-$k$' model trained to generate the target sentence concurrently with the source sentence, but always $k$ words behind, for any given $k$. This framework seamlessly integrates anticipation and translation in a single model that involves only minor changes to the existing neural translation framework. Experiments on Chinese-to-English simultaneous translation achieve a 5-word latency with 3.4 (single-ref) BLEU points degradation in quality compared to full-sentence non-simultaneous translation. We also formulate a new latency metric that addresses deficiencies in previous ones.
Keywords
All Related Versions
This publication has 3 references indexed in Scilit: