Multi-document Summarization via Information Extraction: A Revisit

This paper describes a novel approach of improving multi-document summarization based on cross-document information extraction (IE). We first show that IE itself is not sufficient to produce fluent and coherent summaries. Then we attempt various methods to automatically incorporate IE results into sentence ranking. Experiments have shown our integration methods can significantly improve a high-performing multi-document summarization system, according to the ROUGE-2 and ROUGE-SU4 metrics (7.38%-7.58% relative improvement on ROUGE-2 recall), and the generated summaries are preferred by human subjects (0.78 higher TAC Content score and 0.11 higher Readability/Fluency score).