<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta>
      <journal-title-group>
        <journal-title>the VLDB Journal and the Informa-
tion Systems Journal. Sihem received her Ph.D. in CS from
Univ. Paris</journal-title>
      </journal-title-group>
    </journal-meta>
    <article-meta>
      <title-group>
        <article-title>Crowd-Sourcing Literature Review in SUNFLOWER</article-title>
      </title-group>
      <contrib-group>
        <aff id="aff0">
          <label>0</label>
          <institution>Sihem Amer-Yahia Qatar Computing Research Institute</institution>
          ,
          <addr-line>QCRI</addr-line>
        </aff>
      </contrib-group>
      <pub-date>
        <year>1999</year>
      </pub-date>
      <abstract>
        <p>1. ABSTRACT OF THE INVITED TALK Reviewing literature is painful albeit intellectually rewarding. I will describe SUNFLOWER, a system we developed in collaboration with Bloomsbury, a publisher of scienti c material, member of Qatar Foundation. SUNFLOWER combines the power of search and collaborative editing to review and summarize a large number of articles around a topic. It works in three steps. The rst step performs a composite retrieval of related articles where k bundles of complementary articles are built using article metadata such as authors and citations. The second step associates a summary to each bundle by extracting key phrases from their constituent articles. The last step involves humans that collaboratively edit extracted summaries into a coherent literature review on the topic. We report our experiments on scienti c articles from qscience.com</p>
      </abstract>
    </article-meta>
  </front>
  <body />
  <back>
    <ref-list />
  </back>
</article>