# Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection

arXiv: https://arxiv.org/abs/1810.00668 · HTML: https://mlsanity.com/paper/1810.00668/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2018.

## Built on by (most cited first, 11 of 11)

- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models](https://mlsanity.com/paper/2105.13318/) (2021)
- [Comparison of Grammatical Error Correction Using Back-Translation Models](https://mlsanity.com/paper/2104.07848/) (2021)
- [Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling](https://mlsanity.com/paper/2105.11872/) (2021)
- [Understanding Model Robustness to User-generated Noisy Texts](https://mlsanity.com/paper/2110.07428/) (2021)
- [To Err Is Human, but Llamas Can Learn It Too](https://mlsanity.com/paper/2403.05493/) (2024)
- [Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting](https://mlsanity.com/paper/2310.13321/) (2023)
- [Grammatical Error Generation Based on Translated Fragments](https://mlsanity.com/paper/2104.09933/) (2021)
- [Domain specificity and data efficiency in typo tolerant spell checkers: the case of search in online marketplaces](https://mlsanity.com/paper/2308.01976/) (2023)
- [Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection](https://mlsanity.com/paper/2407.11854/) (2024)
- [Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 Dataset](https://mlsanity.com/paper/2411.15523/) (2024)

## Abstract (arXiv)

Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturallyoccurring errors and attempt to introduce them into other datasets. Initial work on inducing errors in this way using statistical machine translation has shown promise; we investigate cheaply constructing synthetic samples, given a small corpus of human-annotated data, using an off-the-rack attentive sequence-to-sequence model and a straight-forward post-processing procedure. Our approach yields error-filled artificial data that helps a vanilla bi-directional LSTM to outperform the previous state of the art at grammatical error detection, and a previously introduced model to gain further improvements of over 5% F0.5 score. When attempting to determine if a given sentence is synthetic, a human annotator at best achieves 39.39 F1 score, indicating that our model generates mostly human-like instances.