The Representation of Chinese Semantic Knowledge and its Application in the Document Copy Detection

Digital documents are easily copied and distributed ille- gally. Document copy detection is a powerful tool to pro- tect the author´s intellectual property and to improve the efficiency of information retrieval. It is difficult for the ex- isting copy detection systems to identify the sentence struc- ture changed copies. To address the problem, we research the semantic level of natural language processing and pro- pose a document copy detection method based on Chinese semantic knowledge. We introduce the realization mecha- nisms of Chinese language analysis, which contains syn- tactic parsing and semantic analyzing. We also report on the experimental comparison the proposed method with the representative document copy detection systems. The result is satisfying.