Automatically Build Corpora for Chinese Spelling Check Based on the Input Method.

Jianyong Duan Lijian Pan Hao Wang Mei Zhang Mingli Wu

Published in: NLPCC (1) (2019)

Keyphrases

synthetic data
high precision
high accuracy
machine learning
segmentation algorithm
experimental evaluation
cost function
preprocessing
input data
detection method
classification accuracy
computational complexity
bayesian networks
detection algorithm
clustering method
feature selection
neural network
chinese text