Sentence Semantic Similarity based on Word Embedding and WordNet

Semantic similarity between sentences is a crucial task for many applications. The emerging of word embedding encourages calculating similarity between words and between sentences based on the new semantic word representation. On the other hand, WordNet is widely used to find semantic distance between sentences. This paper combines the using of pre-trained word vector and WordNet to measure semantic similarity between two sentences. In addition, word order similarity is applied to make the final similarity more accurate. The proposed approach has been implemented and tested using standard datasets. Experiments show that presented methods achieves better results comparing with other approaches previously proposed to measure sentence similarity.