By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We are developing a multi-document summarization system to automatically generate a concise summary by identifying and synthesizing similarities across a set of related documents. Our approach is unique in its integration of machine learning and statistical techniques to identify similar paragraphs, shallow analysis and comparison to identify similar phrases within paragraphs, and language generation to reformulate the wording of the summary. Our evaluation of system components shows that our use of learning over multiple extracted linguistic features is more effective than information retrieval approaches at identifying similar text units for summarization and that it is possible to generate a fluent summary that conveys similarities among documents even when full semantic interpretations of the input text are not available.
Registration: ISBN 978-0-262-51106-3
Copyright: July 18-22, 1999, Orlando, Florida. Published by The AAAI Press, Menlo Park, California.