This document summarizes a neural approach to grammatical error correction that uses better pre-training and sequential transfer learning. It first discusses previous work on grammatical error correction (GEC) as a low-resource machine translation task and denoising autoencoders. It then describes the authors' approach, which includes context-aware preprocessing, pre-training a model on synthetica
![Java8移行から始めた技術的負債との戦い(jjug ccc 2015 fall)](https://cdn-ak-scissors.b.st-hatena.com/image/square/171fc87e3f067d0c9a1b90402275e3d92ec6fa2f/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Fjava8jjugccc2015fall-151128082013-lva1-app6891-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)