Grammatical error correction in English is a long studied problem with many
existing systems and datasets. However, there has been only a limited research
on error correction of other languages. In this paper, we present a new dataset
AKCES-GEC on grammatical error correction for Czech. We then make experiments
on Czech, German and Russian and show that when utilizing synthetic parallel
corpus, Transformer neural machine translation model can reach new
state-of-the-art results on these datasets. AKCES-GEC is published under CC
BY-NC-SA 4.0 license at this https URL and the source code
of the GEC model is available at
this https URL

本文介绍了一个 Czech 语法纠错的新数据集 AKCES-GEC。我们证明使用合成平行语料库结合 Transformer 神经机器翻译模型可在 Czech，German 和 Russian 等多种语言的数据集上达到新的最高水平。AKCES-GEC 数据集已发表在 CC BY-NC-SA 4.0 许可下，GEC 模型源代码也可访问。

低资源场景下的语法错误修正

Grammatical Error Correction in Low-Resource Scenarios

This paper describes the MeMAD project entry to the WMT Multimodal Machine
Translation Shared Task.
We propose adapting the Transformer neural machine translation (NMT)
architecture to a multi-modal setting. In this paper, we also describe the
preliminary experiments with text-only translation systems leading us up to
this choice.
We have the top scoring system for both English-to-German and
English-to-French, according to the automatic metrics for flickr18.
Our experiments show that the effect of the visual features in our system is
small. Our largest gains come from the quality of the underlying text-only NMT
system. We find that appropriate use of additional data is effective.

本文介绍了 MeMAD 项目进入 WMT 多模式机器翻译共享任务的情况，其中我们提出将 Transformer 神经机器翻译架构适应于多模式环境，并描述了我们在此选择之前对纯文本翻译系统的初步实验。我们拥有英语 - 德语和英语 - 法语两种语言的最高分数系统，在 flickr18 的自动指标中都得到了很好的表现。我们的实验表明，图像特征在我们的系统中作用不大，最大的收益来自于基于纯文本 NMT 系统的质量。我们发现适当地使用其他数据是有效的。