论文标题
提高非自动回归机器翻译的流利度
Improving Fluency of Non-Autoregressive Machine Translation
论文作者
论文摘要
与自动回旋（AR）模型相比，机器翻译（MT）的非自动回旋（NAR）模型表现出了优越的解码速度，以牺牲其输出流利度受损。我们通过在梁搜索解码过程中使用的评分模型中使用其他功能，从而提高了通过连接派时间分类（CTC）的NAR模型的流畅度。由于我们的模型中的光束搜索解码仅需要单个正向通过运行网络，因此解码速度仍然高于标准AR模型中。我们训练三种语言对的模型：德语，捷克语和罗马尼亚语从英语开始。结果表明，我们提出的模型在解码速度方面可以更有效，并且仍然相对于AR模型获得了竞争性的BLEU得分。
Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with connectionist temporal classification (CTC) by employing additional features in the scoring model used during beam search decoding. Since the beam search decoding in our model only requires to run the network in a single forward pass, the decoding speed is still notably higher than in standard AR models. We train models for three language pairs: German, Czech, and Romanian from and into English. The results show that our proposed models can be more efficient in terms of decoding speed and still achieve a competitive BLEU score relative to AR models.
