<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2127">
  <Title>Toward the &amp;quot;At-a-glance&amp;quot; Summary: Phrase-representation Summarization Method YoshihiroUEDA, MamikoOKA, TakahiroKOYAMA and TadanobuMIYAUCHl</Title>
  <Section position="7" start_page="882" end_page="883" type="relat">
    <SectionTitle>
6 Related Work
</SectionTitle>
    <Paragraph position="0"> bllOSt sumnmrization studies (including Zcchnero 1996) arc based on inq3oitant sentence selection and seek belier selection methods. We have +' Generation el&amp;quot; articles is h.'ft to be considered. pointed out that sumnmries made by this method tend to be btndensome to read, and have proposed phrase-representation summarization as an alternative. The following studies bear some relation to our study.</Paragraph>
    <Paragraph position="1"> The summarization method by Boguraev and Kctmedy (1997) adopts ~phrasal expression&amp;quot; rather than sentences or paragraphs. However, it begins to create a phrase not from a core relation but a core word (in their words, &amp;quot;'topic stamp&amp;quot;) and produces multipk; phrases containing the same core word; it is therefore not suitable for summaries for sifting IR results. In addition, because it does not consider the roles and importance of thc attaching arcs when enriching the core, less important words are often attached to the core. They aimed at supporting fast reading rather than sifting IR restllts.</Paragraph>
    <Paragraph position="2"> Some studies are similar to ours in that they make sentences short. Wakao, et al. (1998) and Mikami, ct al. (1998) aim to create closed captioning fl-om an announcer's manuscript by paraf~hrasing and renlovhlg nlodifiers. This method doesnh ronlove \[he &amp;quot;'{l'tlllk ~&amp;quot; o1&amp;quot; the analxsis tree and the sunlll~aries canilot be made as short as in phrase-representation.</Paragraph>
    <Paragraph position="3"> Na{~ao, el al. (1998) also proposed a ineti~od to create summarization based on the i'ehlthms  between words. They utilize GDA (Global Document Annotation), a tag set that the document author inserts into the document and that contains linguistic information such as sentence structures and reference infimnation. Althot@a this method is similar to ours in some points, the stlmmaw consists of sentences and thus does not have &amp;quot;at-a-glalme&amp;quot; capability. Most of all, the expectation that every doctmlent is tagged linguistically will not be fulfilled until special editors with automatic linguistic tagging beconte popular.</Paragraph>
    <Paragraph position="4"> Conclusion We introduced the concept of &amp;quot;at-a-glance&amp;quot; summary and showed an algorithm of phrase-representation SUlnmarization as a realization of the concept. An experiment shows that the summaries are effective for sifting IR results.</Paragraph>
    <Paragraph position="5"> We continue to fine-trine the prototype for timber efficacy.</Paragraph>
  </Section>
class="xml-element"></Paper>