Modeling Dual Read/Write Paths for Simultaneous Machine Translation
Shaolei Zhang, Yan Feng · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
Simultaneous machine translation (SiMT) outputs translation while reading source sentence and hence requires a policy to decide whether to wait for the next source word (READ) or generate a target word (WRITE), the actions of which form a read/write path.Although the read/write path is essential to SiMT performance, no direct supervision is given to the path in the existing methods.In this paper, we propose a method of dual-path SiMT which introduces duality constraints to direct the read/write path.According to duality constraints, the read/write path in source-totarget and target-to-source SiMT models can be mapped to each other.As a result, the two SiMT models can be optimized jointly by forcing their read/write paths to satisfy the mapping.Experiments on En↔Vi and De↔En tasks show that our method can outperform strong baselines under all latency.