论文标题
WMT 22高效翻译共享任务的CUNI非自动入学系统
CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task
论文作者
论文摘要
我们向WMT 22有效翻译共享任务提交了非自动进取系统提交。 Helcl等人使用了我们的系统。 （2022）试图在非自动回归和自回归模型之间进行公平的比较。此提交是为建立固体基线以及合理评估方法的努力，尤其是在测量解码速度方面。该模型本身是一个12层变压器模型，该模型通过强大的自回归教师模型在知识延伸数据集上进行了连接式时间分类训练。
We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.
