Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup.
@article{arxiv.2210.05193,
title = {Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation},
author = {Chenze Shao and Zhengrui Ma and Yang Feng},
journal= {arXiv preprint arXiv:2210.05193},
year = {2023}
}