English

Grammatical Error Correction with Neural Reinforcement Learning

Computation and Language 2017-07-04 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1707.00299,
  title  = {Grammatical Error Correction with Neural Reinforcement Learning},
  author = {Keisuke Sakaguchi and Matt Post and Benjamin Van Durme},
  journal= {arXiv preprint arXiv:1707.00299},
  year   = {2017}
}
R2 v1 2026-06-22T20:35:34.339Z