This paper discusses an approach to topic-oriented multi-document summarization. It investigates the effectiveness of using
additional information about the document set as a whole, as well as individual documents. We present NEO-CORTEX, a multi-document
summarization system based on the existing CORTEX system. Results are reported for experiments with a document base formed
by the NIST DUC-2005 and DUC-2006 data. Our experiments have shown that NEO-CORTEX is an effective system and achieves good
performance on topic-oriented multi-document summarization task.
Keywords Automatic summarization - Statistical methods - Text mining - Query guided summaries