Paper Info
Title
A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation
Abstract
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenge to the standard cross entropy (XE) loss in NAT and is under studied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to use different loss functions for different kinds of syntactic multi-modality.
Year
DOI
Venue
2022
10.18653/V1/2022.NAACL-MAIN.126
North American Chapter of the Association for Computational Linguistics (NAACL)
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Kexun Zhang100.34
Wang Rui201.69
Xu Tan38823.94
Junliang Guo472.44
Ren, Yi5104.35
Tao Qin62384147.25
Tie-yan Liu74662256.32