Chinese Sentence Similarity Based on Multi-feature Combination

The Chinese sentence similarity computation has been used widely in the field of Chinese information processing. Many methods have been proposed to measure the similarity of Chinese sentences, but they focus mainly on one or two features, e.g. words, structure or semantic information and so on. The accuracy of these methods is usually lower. In this paper, we present a new approach to compute the similarity of Chinese sentences based on multi-feature combination. This method defines the key features in similarity computation and then combines their contribution to obtain the sentence similarity. Experiments show that this method has higher accuracy in Chinese sentence similarity computation.