Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

TL;DR

This paper introduces a non-autoregressive Transformer-based cascaded model that enables end-to-end training for sequence-to-sequence tasks, reducing error propagation and improving translation quality.

Contribution

It proposes a novel architecture that allows end-to-end training without explicit intermediate representations, addressing key issues in traditional cascaded models.

Findings

Over 2 BLEU improvement on French-German translation

Effective end-to-end training without intermediate data

Reduces error propagation in cascaded models

Abstract

Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no possibility of using end-to-end training data in conventional cascaded systems, meaning that the training data most suited for the task cannot be used. Previous studies suggested several approaches for integrated end-to-end training to overcome those problems, however they mostly rely on (synthetic or natural) three-way data. We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. This new architecture (i) avoids unnecessary early decisions that can cause errors which are then propagated throughout the cascaded models and (ii) utilizes the end-to-end training data directly. We conduct an evaluation on two pivot-based machine translation tasks, namely French-German and German-Czech. Our experimental results show that the proposed architecture yields an improvement of more than 2 BLEU for French-German over the cascaded baseline.