Chinese question similarity calculation based on word sense disambiguation

The sentence similarity computation plays an significant role in the fields of Chinese language processing. The paper presents a new approach to calculate the Chinese question semantic similarity, which is divided into two steps: the first step is to disambiguate the word sense in the question, and the second step is to compute the question semantic similarity based on the word sense. This paper uses HowNet to disambiguate the word sense and to calculate the sense similarity. The experimental results show that the proposed algorithm worked more reasonable in the real calculation and out-performs the conventional computed approaches.