Detecting Grammatical Errors in the NTOU CGED System by Identifying Frequent Subsentences

Abstract

The main goal of Chinese grammatical error diagnosis task is to detect word errors in the sentences written by Chinese-learning students. Our previous system would generate error-corrected sentences as candidates and their sentence likelihood were measured based on a large scale Chinese n-gram dataset. This year we further tried to identify long frequently-seen subsentences and label them as correct in order to avoid propose too many error candidates. Two new methods for suggesting missing and selection errors were also tested.