<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-4006">
  <Title>QCS: A Tool for Querying, Clustering, and Summarizing Documents</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> QCS is a software tool and development framework for efficient, organized, and streamlined IR from generic document sets. The system is designed to match a query to relevant documents, cluster the resulting subset of documents by topic, and produce a single summary for each topic. Using QCS for IR, the amount of redundant information presented to a user is reduced and the results are categorized by content.</Paragraph>
    <Paragraph position="1"> A survey of previous work using a combination of clustering and summarization to improve IR can be found in Radev et al. (2001b). Of existing IR systems employing this combination, QCS most resembles the NewsInEssence system (Radev et al., 2001a) in that both systems can produce multi-document summaries from document sets clustered by topic. However, NewsInEssence is designed for IR from HTML-linked document sets and QCS has been designed for IR from generic document sets. Furthermore, one of the most important aspects of QCS is its modularity, with the ability to plug in alternative implementations of query-based retrieval, document clustering, and summarization algorithms.</Paragraph>
  </Section>
class="xml-element"></Paper>