Compositional Sequence Labeling Models for Error Detection in Learner Writing
Marek Rei, Helen Yannakoudakis
Abstract
In this paper, we present the first experiments using neural network models for the task of error detection in learner writing. We perform a systematic comparison of alternative compositional architectures and propose a framework for error detection based on bidirectional LSTMs. Experiments on the CoNLL-14 shared task dataset show the model is able to outperform other participants on detecting errors in learner writing. Finally, the model is integrated with a publicly deployed self-assessment system, leading to performance comparable to human annotators.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Grammatical Error Correction | CoNLL-2014 A1 | F0.5 | 34.3 | Bi-LSTM (unrestricted data) |
| Grammatical Error Correction | CoNLL-2014 A1 | F0.5 | 16.4 | Bi-LSTM (trained on FCE) |
| Grammatical Error Correction | CoNLL-2014 A2 | F0.5 | 44 | Bi-LSTM (unrestricted data) |
| Grammatical Error Correction | CoNLL-2014 A2 | F0.5 | 23.9 | Bi-LSTM (trained on FCE) |
| Grammatical Error Correction | FCE | F0.5 | 41.1 | Bi-LSTM |
Related Papers
IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator2025-06-03Detecting Spelling and Grammatical Anomalies in Russian Poetry Texts2025-05-07ARWI: Arabic Write and Improve2025-04-16Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 Dataset2024-11-23Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification2024-11-13GECTurk WEB: An Explainable Online Platform for Turkish Grammatical Error Detection and Correction2024-10-16Oddballness: universal anomaly detection with language models2024-09-04Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection2024-07-16