Grammatical Error Correction with Neural Reinforcement Learning
This addresses grammatical error correction for language processing applications, representing an incremental improvement over existing methods.
The paper tackled grammatical error correction by proposing a neural encoder-decoder model with reinforcement learning that directly optimizes for sentence-level metrics, achieving state-of-the-art results on a fluency-oriented corpus.
We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE. We demonstrate that NRL outperforms MLE both in human and automated evaluation metrics, achieving the state-of-the-art on a fluency-oriented GEC corpus.