论文标题
发动机：非自动入学机器翻译的基于能量的推理网络
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
论文作者
论文摘要
我们建议训练非自动回旋的机器翻译模型，以最大程度地减少预验证的自回旋模型所定义的能量。特别是，我们将非自动回归翻译系统视为推理网络（Tu and Gimpel，2018），训练有素，可以最大程度地减少自回归教师的能量。这与训练非自动回归模型的流行方法形成鲜明对比，该模型是由这种教师模型的横梁搜索输出组成的。我们称为引擎（基于能量的推理网络）的方法，在IWSLT 2014 DE-EN和WMT 2016 RO-EN数据集上取得了最新的非自动回归结果，以接近自动性模型的性能。
We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel, 2018) trained to minimize the autoregressive teacher energy. This contrasts with the popular approach of training a non-autoregressive model on a distilled corpus consisting of the beam-searched outputs of such a teacher model. Our approach, which we call ENGINE (ENerGy-based Inference NEtworks), achieves state-of-the-art non-autoregressive results on the IWSLT 2014 DE-EN and WMT 2016 RO-EN datasets, approaching the performance of autoregressive models.
