A Simple but Effective Classification Model for Grammatical Error Correction
This provides an effective solution for grammatical error correction, suitable for industrial applications, though it appears incremental as it builds on existing classification approaches.
The paper tackles grammatical error correction by framing it as a classification problem, using a neural network with RNNs and attention to represent context, and achieves an F0.5 score of 45.05% on the CoNLL-2014 test set, outperforming other classifier methods.
We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We propose a novel neural network based feature representation and classification model, trained using large text corpora without human annotations. Specifically we use RNNs with attention to represent both the left and right context of a target word. All feature embeddings are learned jointly in an end-to-end fashion. Experimental results show that our novel approach outperforms other classifier methods on the CoNLL-2014 test set (F0.5 45.05%). Our model is simple but effective, and is suitable for industrial production.