Study on the Application of Fuzzy KNN to Chinese and English Recognition

Abstract

Automated Chinese and English recognition is defined as the process of assigning category labels to new documents based on the likelihood suggested by a training set of labelled documents.A study on the performance of fuzzy KNN for Chinese and English recognition is presented.Four famous approaches to text feature selection are adopted.The improved fuzzy KNN method is compared to the conventional KNN method and the KNN method based on similarity-weighting.and the experimental results show that the proposed method can weaken the impact of the disparity of training samples in distribution on categorization performance with different feature selection methods selected.Also,the categorization accuracy is improved,and the sensitivity to Kvalue is reduced to some extent.