NUS at DUC 2005: Understanding Documents via Concept Links
Shiren Ye, Long Qiu, Tat‐Seng Chua, Min‐Yen Kan · 2005
The primary goal of our participation in DUC 2005 is two-fold. One is to benchmark the performance of a method of computing sentence semantic similarity. The other is to test the effectiveness of a new redundancy minimization formula inspired by Maximal Marginal Relevance (MMR). By using only these two features and eschewing other heuristics, our system performed competitively, achieving the top automated ROUGE scores among participants this year. This is a revised version of our notebook paper. 1