<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1213">
  <Title>I I I I I I I I I I I I I I I I I Automatically generating hypertext in newspaper articles by computing semantic relatedness</Title>
  <Section position="8" start_page="22806" end_page="22806" type="concl">
    <SectionTitle>
6 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> Our evaluation shows that we cannot reject our null hypothesis that there is no difference in the two methods for generating inter-article links. Having said this, we can demonstrate a partition of the subjects such that the only significant differences between them are the number of HT links followed and the number of answers found. Furthermore, we determined that the probability of obtaining results such as these by chance is less than 0.1. Our inability to achieve a significant result may be due to several implementation factors, described in Green (1997). Thus, we conclude that we need to replicate the experiment in order to gain further information about the relationship between the two kinds of inter-article links.</Paragraph>
    <Paragraph position="1"> Green 109 Automatically generating hypertext</Paragraph>
  </Section>
class="xml-element"></Paper>