Toward Multi-document summarization by Reformulation: progress

By synthesizing information common to retrieved docu-ments, multi-document summarization can help users of in-formation 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, intersection of similar phrases within paragraphs, and language generation to reformulate the wording of the summary. Our evaluation of system com-ponents shows that learning over multiple extracted linguis-tic features is more effective than information retrieval ap-proaches at identifying similar text units for summarization and that it is possible to generate a fluent summary that con-veys similarities among documents even when full semantic interpretations of the input text are not available