Microblog Summarization via Enriching Contextual Features Based on Sentence-Level Semantic Analysis

A novel microblog summarization approach via enriching contextual features on sentence-level semantic analysis is proposed in this paper. At first, a Chinese sentential semantic model (CSM) is employed to analyze the semantic structure of each microblog sentence. Then, a combination of sentence-level semantic analysis and latent dirichlet allocation is utilized to acquire extra features and related words to enrich the collection of microblog messages. The simlilarites between the two sentences are calculated based on the enriched features. Finally, the semantic weight and relation weight are calculated to select the most informative sentences, which form the final summary for microblog messages. Experimental results demonstrate the advantages of our proposed approach. The results indicate that introducing sentence-level semantic analysis for context enrichment can better represent sentential semantic. The proposed criteria, namely, semantic weight and relation weight enhance summary result. Furthermore, CSM is a useful framework for sentence-level semantic analysis.