<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-2022">
  <Title>Multilingual Term Extraction from Domain-specific Corpora Using Morphological Structure</Title>
  <Section position="5" start_page="173" end_page="173" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a method for the automatic acquisition of terms from domain-specific texts using morphological structure. The method also groups terms in morphological families. Families are displayed as a weighted list, thus giving an instant overview of the main topics in the corpus under study. Results obtained from the first experiments confirm the usefulness of a morphological pattern based approach for the extraction of terms from domain-specific corpora and especially medical texts. The method for the identification of compound words could be improved by an automatic approach to morphological segmentation as done by (Creutz and Lagus, 2004). Term clustering could be ameliorated as well by investigating the usefulness of stemming to avoid underconflation. null</Paragraph>
  </Section>
class="xml-element"></Paper>