Summarising News with Texts and Pictures

摘要

As the information explosion is becoming more and more seriously, effective and efficient multi-document summarization techniques are becoming more and more necessary. Previous document summarization approaches mainly focus on texts. The poor readability of summaries prevents these approaches from widely practical use. This paper proposes a novel multi-document summarization approach to summarizing news documents by incorporating relevant pictures to improve the readability of summary. We construct a unified semantic link network on concepts, sentences and pictures, and then propose a mutual reinforcement network method to calculate the saliency scores of the concepts, pictures and sentences simultaneously. An Integer Liner Programming (ILP) model is used to select the important, closely related and succinct sentences and pictures. Experiments show that our approach can generate more readable and understandable summary.