Automatically Generating the Chinese News Summary Based on Fuzzy Reasoning and Domain Ontology

• Main Authors: Ming-Hung Huang, 黃名宏
• Other Authors: Shyi-Ming Chen
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/42v5c3

碩士 === 國立臺灣科技大學 === 資訊工程系 === 100 === In this thesis, we present a new method for automatically generating the Chinese weather news summary based on fuzzy reasoning and the domain ontology, where the weather ontology, the time ontology and the geography ontology are predefined by domain experts. We slice the original Chinese weather news articles into a set of terms. Then, we use two ontological features (i.e., the degree of depth of the ontology and the degree of width of the ontology) and one statistical feature (i.e., the frequency) as inputs of the system. The values of those features are represented by fuzzy sets. Then, the fuzzy reasoning mechanism calculates the score of each sentence. The summary is composed of candidate sentences which have higher scores, where the experimental data are adopted from the Chinese weather news website of Taiwan. The experimental results show that the proposed method outperforms the methods presented in [14] and [15] for automatically generating the Chinese news summary.