Aligned Cross Entropy for Non-Autoregressive Machine Translation

Marjan Ghazvininejad · Vladimir Karpukhin · Luke Zettlemoyer · Omer Levy

Keywords: [ Deep Sequence Models ] [ Natural Language Processing / Dialogue ] [ Applications - Language, Speech and Dialog ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links


Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoregressive factors in the model. This difficultly is compounded during training with cross entropy loss, which can highly penalize small shifts in word order. In this paper, we propose aligned cross entropy (AXE) as an alternative loss function for training of non-autoregressive models. AXE uses a differentiable dynamic program to assign loss based on the best possible monotonic alignment between target tokens and model predictions. AXE-based training of conditional masked language models (CMLMs) substantially improves performance on major WMT benchmarks, while setting a new state of the art for non-autoregressive models.

Chat is not available.