A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation

TL;DR

This paper systematically investigates the syntactic multi-modality problem in non-autoregressive machine translation, proposing a new loss function that combines strengths of existing methods to better handle complex syntactic variations.

Contribution

It decomposes syntactic multi-modality into short- and long-range types, evaluates existing loss functions, and designs a new combined loss for improved translation quality.

Findings

CTC loss handles short-range syntactic multi-modality well.

OAXE loss is effective for long-range syntactic multi-modality.

A new combined loss improves handling of complex syntactic variations.

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.