<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1082">
  <Title>A step towards the detection of semantic variants of terms in technical documents</Title>
  <Section position="5" start_page="503" end_page="503" type="concl">
    <SectionTitle>
5 Conclusion and future works
</SectionTitle>
    <Paragraph position="0"> The use of a synonym dictionary and the rules of synonymous candidate terms detection we have designed allow to extract an encouraging number of links in a very technical corpus. An expert validated these links. More than one third of the detected links are synonymy relations.</Paragraph>
    <Paragraph position="1"> Beside synonymy, our method detects various kinds of semantic variants. Wrong links due to the polysemy can be easily eliminated with exception rules by comparing selectional patterns and generalized contexts (Basili et al., 1993; Grishman and Sterling, 1994).</Paragraph>
    <Paragraph position="2"> Our work shows that general semantic data are useful for the terminology structuration and the synonym detection in a corpus of specialized language. The results show that semantic variants can be automatically detected. Of course, the number of acquired links is relatively low but our method is not to be used in isolation.</Paragraph>
  </Section>
class="xml-element"></Paper>