Chinese word similarity computing

This paper studies Chinese word similarity computing. A 3D model is proposed for representing word meaning based on different points of view. The first one is the view of primitive from Hownet, the second one is the view of words´ occurrence in sentences from a specific corpus, and the third one is the view of well known background knowledge from online resources. A Chinese content word is represented in a 3D model. Similarity of two words is computed according to it. Experiments on Chinese news have shown that this method could perform better than existed ones based only on one point of view.