Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Chenze Shao, Zhengrui Ma, Yang Feng
Abstract
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.
BibTeX
@inproceedings{shao-etal-2022-viterbi,
title = "{V}iterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation",
author = "Shao, Chenze and
Ma, Zhengrui and
Feng, Yang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.322/",
doi = "10.18653/v1/2022.findings-emnlp.322",
pages = "4390--4397"
}