In this paper, we present a novel approach for automatic summarization. Our system, called CBSEAS, integrates a new method to detect redundancy at its very core, and produce more expressive summaries than previous approaches. Moreover, we show that our system is versatile enough to integrate opinion mining techniques, so that it is capable of producing opinion oriented summaries. The very competitive results obtained during the last Text Evaluation Conference (TAC 2008) show that our approach is efficient. .
