Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data
This work addresses data scarcity in GEC, a domain-specific task for improving text quality, and is incremental as it builds on existing neural translation methods with novel pre-training and copying techniques.
The paper tackled the problem of limited labeled data in Grammatical Error Correction (GEC) by pre-training a copy-augmented neural architecture with unlabeled data, resulting in state-of-the-art performance on the CoNLL-2014 test set with a large margin improvement.
Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged words from the source sentence to the target sentence. Since the GEC suffers from not having enough labeled training data to achieve high accuracy. We pre-train the copy-augmented architecture with a denoising auto-encoder using the unlabeled One Billion Benchmark and make comparisons between the fully pre-trained model and a partially pre-trained model. It is the first time copying words from the source context and fully pre-training a sequence to sequence model are experimented on the GEC task. Moreover, We add token-level and sentence-level multi-task learning for the GEC task. The evaluation results on the CoNLL-2014 test set show that our approach outperforms all recently published state-of-the-art results by a large margin. The code and pre-trained models are released at https://github.com/zhawe01/fairseq-gec.