Template Based Chinese News Event Summarization

Summarization can facilitate users to acquire large amount of information. This paper introduces a Chinese news events summarization system based on a predefined template. The system automatically collects query-related news online, applies Language model to detect event related information, calculates word frequencies based on semantic meaning and uses information fusion techniques to merge the results. After experiments on 50 events, the system can achieve the average of 82.1% precision based on human judgment.