A novel semantic similarity measure within sentences

This paper presents a novel sentence similarity computation algorithm. We thought that the complete expression of a short sentence, not only depends on the syntactic structure, but also relies on the words and their weight, thus this method take word similarity feature and syntactic feature into account. The proposed method can be used in a variety of applications involving text knowledge representation, automatic document summarization, and knowledge discovery. The experiment demonstrates that the proposed algorithm has outstanding performance in handling with short sentences with complex syntax.