Grammatical Error Correction with Neural Reinforcement Learning
international joint conference on natural language processing, 2017.
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 demonst...More
PPT (Upload PPT)