Context is Key: Grammatical Error Detection with Contextual Word Representations
This addresses the problem of limited and imbalanced datasets for grammatical error detection, benefiting language learners and educators, though it is incremental as it builds on existing methods.
The paper tackled grammatical error detection in non-native writing by systematically comparing and integrating contextual word representations like ELMo, BERT, and Flair embeddings, achieving a new state of the art on public GED datasets.
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.