Grammatical Error Detection and Correction using a Single Maximum Entropy Model
Peilu Wang, Zhongye Jia, Hai Zhao · 2014
This paper describes the system of Shang-hai Jiao Tong Unvierity team in the CoNLL-2014 shared task. Error correc-tion operations are encoded as a group of predefined labels and therefore the task is formulized as a multi-label classifica-tion task. For training, labels are obtained through a strict rule-based approach. For decoding, errors are detected and correct-ed according to the classification results. A single maximum entropy model is used for the classification implementation in-corporated with an improved feature selec-tion algorithm. Our system achieved pre-cision of 29.83, recall of 5.16 and F 0.5 of 15.24 in the official evaluation. 1