<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0404">
  <Title>Revisions that Improve Cohesion in Multi-document Summaries: A Preliminary Study</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> This paper represents preliminary work in our efforts to address problems of text cohesion and coherence in multi-document summaries via revision.</Paragraph>
    <Paragraph position="1"> As a first step, we need to identify the specific problems that occur in MDS and consider how we might address such concerns. To this end, we have investigated the optimal revisions that were performed on a small set of summaries. From this analysis, we have formulated a taxonomy of pragmatic concerns and their operators for repairing multi-document summaries.</Paragraph>
    <Paragraph position="2">  There is a scale of revision operations that can be performed (as shown in Figure 3), ranging from concrete repairs that require only knowledge of the surface structures of sentences, to knowledge-intensive repairs that cannot be implemented without a discourse model. In the future, we plan to formalize our framework so that we might be able to implement such revision strategies automatically. Of course, such an automatic process will be much more constrained in the revisions it can apply, unlike the human reviser in our current study. For example, in automating the repair process we will be restricted to using only material from the source documents. In addition, we may expand our taxonomy as necessary in exploring additional data. We will need to relate revision in MDS to CST since revision required in a given summary depends on the relationships between sentences.</Paragraph>
    <Paragraph position="3"> Finally, we would like use the corpus of data we have collected to learn revision automatically.</Paragraph>
  </Section>
class="xml-element"></Paper>