<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0713">
  <Title>From discourse structures to text summaries</Title>
  <Section position="6" start_page="87" end_page="87" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We deserthed the first experiment that shows that the concepts of rhetorical analysts and nucleanty can be used effecUvely for suramannng text The expemnent suggests that discourse-based methods can account for determining the most zmportant umts m a text w~th a recall and precision as high as 70% We Showed how the concepts of rbetoncal analysts and nucleanty can be treated algonthmtcally and we compared recall and preclsmn figures of a summanzauon program that implements these concepts with recall and prects~on figures that pertmn to a basehne algonthm and to a c6mmerclal system, the MlcrosoR Of.</Paragraph>
    <Paragraph position="1"> rice97 summarizer The discourse-based summanzauon program that we propose outperforms both the basehne and the commercial summarizer (see table 3) However, since ~ts results do not match yet the recall and precision figures that pertmn to the manual discourse analyses, zt zs likely that improvements of the rhetorical parser algorithm wall result m better performance of subsequent Lmplemetat~ons Acknowledgements. I am grateful to Graeme Htrst for the .invaluable help he gave me dunng every stage of tins work and to Marllyn Mantel, David Mitchell, Kevm Schlueter, and Melame Baljko for their advice on experimental design and stanstlcs I am also grateful to Marzena Makuta for her help with the RST analyses and to my colleagues and friends who volunteered to act as judges m the experiments described here Tins reasearch was supported by the Natural Sciences and Engineering Research Council of Canada</Paragraph>
  </Section>
class="xml-element"></Paper>