Paper: POSTECH Grammatical Error Correction System in the CoNLL-2014 Shared Task

ACL ID W14-1709
Title POSTECH Grammatical Error Correction System in the CoNLL-2014 Shared Task
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2014
Authors

This paper describes the POSTECH gram- matical error correction system. Various methods are proposed to correct errors such as rule-based, probability n-gram vector approaches and router-based ap- proach. Google N-gram count corpus is used mainly as the correction resource. Correction candidates are extracted from NUCLE training data and each candidate is evaluated with development data to ex- tract high precision rules and n-gram frames. Out of 13 participating teams, our system is ranked 4th on both the original and revised annotation.