Yllias Chali, Stan Matwin, and Stan Szpakowicz
Text summarization may soon become a competitive method of answering queries asked of large text corpora. A query brings up a set of documents. These documents are then filtered by a summarizer: it constructs brief summaries from document fragments conceptually close to the query terms. We present the implementation of such a summarization system, based on lexical semantics, and discuss its operation. It is a configurable system, in the sense that the user will be able to choose among two or more implementations of every major step.