Automatically generating the weather news summary based on fuzzy reasoning and ontology techniques

In this paper, we present a new method for automatically generating the weather news summary based on fuzzy reasoning and ontology techniques, where the weather ontology, the time ontology and the geography ontology are predefined by domain experts. We slice the original 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., frequency) as inputs to the system. The values of those features are represented by fuzzy sets. Then, the fuzzy reasoning algorithm infers the score of each sentence. The summary is composed of candidate sentences which have higher scores, where the experimental data are adopted from the weather news website of Taiwan. The experimental results show that the proposed method outperforms the methods presented in [14], [15] for automatically generating the weather news summary.