# A BERT-based Unsupervised Grammatical Error Correction Framework

arXiv: https://arxiv.org/abs/2303.17367 · HTML: https://mlsanity.com/paper/2303.17367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)
- [Grammatical Error Correction: A Survey of the State of the Art](https://mlsanity.com/paper/2211.05166/) (2022)
- [LM-Critic: Language Models for Unsupervised Grammatical Error Correction](https://mlsanity.com/paper/2109.06822/) (2021)
- [Data Weighted Training Strategies for Grammatical Error Correction](https://mlsanity.com/paper/2008.02976/) (2020)
- [Neural Grammatical Error Correction with Finite State Transducers](https://mlsanity.com/paper/1903.10625/) (2019)
- [Distilling the Knowledge of BERT for CTC-based ASR](https://mlsanity.com/paper/2209.02030/) (2022)
- [Mining Error Templates for Grammatical Error Correction](https://mlsanity.com/paper/2206.11569/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction](https://mlsanity.com/paper/2410.20838/) (2024)

## Abstract (arXiv)

Grammatical error correction (GEC) is a challenging task of natural language processing techniques. While more attempts are being made in this approach for universal languages like English or Chinese, relatively little work has been done for low-resource languages for the lack of large annotated corpora. In low-resource languages, the current unsupervised GEC based on language model scoring performs well. However, the pre-trained language model is still to be explored in this context. This study proposes a BERT-based unsupervised GEC framework, where GEC is viewed as multi-class classification task. The framework contains three modules: data flow construction module, sentence perplexity scoring module, and error detecting and correcting module. We propose a novel scoring method for pseudo-perplexity to evaluate a sentence's probable correctness and construct a Tagalog corpus for Tagalog GEC research. It obtains competitive performance on the Tagalog corpus we construct and open-source Indonesian corpus and it demonstrates that our framework is complementary to baseline method for low-resource GEC task.