A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction

TL;DR

This paper introduces a multilayer convolutional encoder-decoder neural network that significantly improves grammatical error correction by leveraging character N-gram embeddings and outperforms previous neural and statistical methods on benchmark datasets.

Contribution

The authors propose a novel convolutional neural network architecture with character N-gram embeddings that surpasses existing neural and statistical approaches in grammatical error correction.

Findings

Outperforms all prior neural approaches on CoNLL-2014 and JFLEG datasets.

Convolutional networks outperform LSTM-based models in capturing local context.

Ensembling and rescoring techniques further improve correction quality.

Abstract

We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neural approaches on this task as well as strong statistical machine translation-based systems with neural and task-specific features trained on the same data. Our analysis shows the superiority of convolutional neural networks over recurrent neural networks such as long short-term memory (LSTM) networks in capturing the local context via attention, and thereby improving the coverage in correcting grammatical errors. By ensembling multiple models, and incorporating an N-gram language model and edit features via rescoring, our novel method becomes the first neural approach to outperform the current state-of-the-art statistical machine translation-based approach, both in terms of grammaticality and fluency.