Overview of DUC 2006
Hoa Trang Dang · 2006
The DUC 2006 summarization task was to synthesize from a set of 25 documents a wellorganized, fluent answer to a complex question. The task and evaluation measures were basically the same as in DUC 2005, except that an additional “overall ” responsiveness measure was added which took into account both content and readability of the summary. The average performance of systems in 2006 was noticeably better than in 2005; systems achieved better focus on average, and many attempted to provide greater coherence to their summaries. The overall responsiveness metric showed that readability plays an important role in the perceived quality of the summaries. 1