Paper: A Unified Framework for Grammar Error Correction

ACL ID W14-1713
Title A Unified Framework for Grammar Error Correction
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2014

In this paper we describe the PKU system for the CoNLL-2014 grammar error cor- rection shared task. We propose a unified framework for correcting all types of er- rors. We use unlabeled news texts instead of large amount of human annotated texts as training data. Based on these data, a tri-gram language model is used to cor- rect the replacement errors while two extra classification models are trained to correct errors related to determiners and preposi- tions. Our system achieves 25.32% in f 0.5 on the original test data and 29.10% on the revised test data.