Non-autoregressive approaches aim to improve the inference speed of
translation models, particularly those that generate output in a one-pass
forward manner. However, these approaches often suffer from a significant drop
in translation quality compared to autoregressive models. This paper introduces
a series of innovative techniques to enhance the translation quality of
Non-Autoregressive Translation (NAT) models while maintaining a substantial
acceleration in inference speed. We propose fine-tuning Pretrained Multilingual
Language Models (PMLMs) with the CTC loss to train NAT models effectively.
Furthermore, we adopt the MASK insertion scheme for up-sampling instead of
token duplication, and we present an embedding distillation method to further
enhance performance. In our experiments, our model outperforms the baseline
autoregressive model (Transformer \textit{base}) on multiple datasets,
including WMT'14 DE$\leftrightarrow$EN, WMT'16 RO$\leftrightarrow$EN, and
IWSLT'14 DE$\leftrightarrow$EN. Notably, our model achieves better performance
than the baseline autoregressive model on the IWSLT'14 En$\leftrightarrow$De
and WMT'16 En$\leftrightarrow$Ro datasets, even without using distillation data
during training. It is worth highlighting that on the IWSLT'14
DE$\rightarrow$EN dataset, our model achieves an impressive BLEU score of
39.59, setting a new state-of-the-art performance. Additionally, our model
exhibits a remarkable speed improvement of 16.35 times compared to the
autoregressive model.

通过使用 CTC loss 进行微调 PMLM 模型、采用 MASK 插入方案进行上采样、使用嵌入蒸馏方法进一步提高性能，使得非自回归模型获得了更好的翻译质量和加速，并在多个数据集上优于自回归模型

使用预训练语言模型、嵌入蒸馏和上采样策略改善 CTC 非自回归翻译质量

Improving Non-autoregressive Translation Quality with Pretrained  Language Model, Embedding Distillation and Upsampling Strategy for CTC

We present a new software package designed to reduce the computational burden
of hadron collider measurements in Parton Distribution Function (PDF) fits. The
APFELgrid package converts interpolated weight tables provided by APPLgrid
files into a more efficient format for PDF fitting by the combination with PDF
and $\alpha_s$ evolution factors provided by APFEL. This combination
significantly reduces the number of operations required to perform the
calculation of hadronic observables in PDF fits and simplifies the structure of
the calculation into a readily optimised scalar product. We demonstrate that
our technique can lead to a substantial speed improvement when compared to
existing methods without any reduction in numerical accuracy.

本文介绍的新软件包可大大改善强子对撞机测量中的 Parton Distribution Function (PDF) 拟合计算负担，从而实现了数值精度不变的前提下，显著提升计算速度。