Topic-Focused Summarization of News Events Based on Biased Snippet Extraction and Selection

In this paper, we propose a framework to produce topic-focused summarization of news events, based on biased snippet extraction and selection. Through our approach, a summarization only retaining information related to a predefined topic (e.g. economy or politics) can be generated for a given news event to satisfy users with specific interests. To better balance coherence and coverage of the summarization, snippets rather than sentences or paragraphs are used as textual components. Topic signature is employed in snippet extraction and selection in order to emphasize the topic-biased information. Experiments conducted on real data demonstrate a good coverage, topic-relevancy, and content coherence of the summaries generated by our approach.