NUS at DUC 2007: Using Evolutionary Models of Text

This paper presents our new, querybased multi-document summarization system used in DUC 2007. Current graph-based approaches to text summarization, such as TextRank and LexRank, assume a static graphmodel which does not model how input text emerges. A suitable evolutionary graph model that is related to human writing/reading process may impart a better understanding of the text and improve the subsequent summarization process. We propose a timestamped graph (TSG) model motivated by human writing and reading processes, and show how input text emerges under the construction phase of TSG. We applied TSG on both the main task and update summary task in Document Understanding Conferences (DUC) 2007 and achieved satisfactory results. We also suggested a modified MMR re-ranker for the update task.