# Context is Key: Grammatical Error Detection with Contextual Word Representations

## TL;DR

This paper systematically compares contextual word embeddings like ELMo, BERT, and Flair for grammatical error detection in non-native writing, achieving state-of-the-art results by integrating these representations effectively.

## Contribution

It provides a comprehensive comparison of contextual embeddings for GED and introduces an effective method to incorporate them, setting new performance benchmarks.

## Key findings

- BERT and Flair outperform ELMo in GED tasks.
- Effective integration of contextual embeddings improves error detection accuracy.
- Analysis reveals different embeddings excel at detecting specific error types.

## Abstract

Grammatical error detection (GED) in non-native writing requires systems to identify a wide range of errors in text written by language learners. Error detection as a purely supervised task can be challenging, as GED datasets are limited in size and the label distributions are highly imbalanced. Contextualized word representations offer a possible solution, as they can efficiently capture compositional information in language and can be optimized on large amounts of unsupervised data. In this paper, we perform a systematic comparison of ELMo, BERT and Flair embeddings (Peters et al., 2017; Devlin et al., 2018; Akbik et al., 2018) on a range of public GED datasets, and propose an approach to effectively integrate such representations in current methods, achieving a new state of the art on GED. We further analyze the strengths and weaknesses of different contextual embeddings for the task at hand, and present detailed analyses of their impact on different types of errors.