NEO-CORTEX: A Performant User-Oriented Multi-Document Summarization System

Abstract. This paper discusses an approach to topic-oriented multidocument 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 NEOCORTEX is an effective system and achieves good performance on topicoriented multi-document summarization task. Key words: Automatic summarization, Statistical methods, Text mining, Query guided summaries

• Type: Conference
• Year: 2007
• Where: CICLING
• Authors: Florian Boudin, Juan Manuel Torres Moreno
• Keywords: CICLING 2007, Multi-document Summarization, Natural Language Processing, Topic-oriented Multidocument Summarization, Topicoriented Multi-document Summarization