# Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction

arXiv: https://arxiv.org/abs/1605.06353 · HTML: https://mlsanity.com/paper/1605.06353/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2016.

## Built on by (most cited first, 8 of 8)

- [Grammatical Error Correction: A Survey of the State of the Art](https://mlsanity.com/paper/2211.05166/) (2022)
- [Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation](https://mlsanity.com/paper/2305.14734/) (2023)
- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [Towards Lithuanian grammatical error correction](https://mlsanity.com/paper/2203.09963/) (2022)
- [Neural Grammatical Error Correction for Romanian](https://mlsanity.com/paper/2604.23627/) (2026)
- [A Language Model for Grammatical Error Correction in L2 Russian](https://mlsanity.com/paper/2307.01609/) (2023)
- [Time Is Effort: Estimating Human Post-Editing Time for Grammar Error Correction Tool Evaluation](https://mlsanity.com/paper/2510.04394/) (2025)
- [STAGEET: Stage-wise Typed Edit Tagging for Grammatical Error Correction with Arabic as a Case Study](https://mlsanity.com/paper/2608.28614/) (2026)

## Abstract (arXiv)

In this work, we study parameter tuning towards the M^2 metric, the standard metric for automatic grammar error correction (GEC) tasks. After implementing M^2 as a scorer in the Moses tuning framework, we investigate interactions of dense and sparse features, different optimizers, and tuning strategies for the CoNLL-2014 shared task. We notice erratic behavior when optimizing sparse feature weights with M^2 and offer partial solutions. We find that a bare-bones phrase-based SMT setup with task-specific parameter-tuning outperforms all previously published results for the CoNLL-2014 test set by a large margin (46.37% M^2 over previously 41.75%, by an SMT system with neural features) while being trained on the same, publicly available data. Our newly introduced dense and sparse features widen that gap, and we improve the state-of-the-art to 49.49% M^2.