<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2083">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Term Recognition Approach to Acronym Recognition</Title>
  <Section position="7" start_page="649" end_page="649" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper we described a term recognition approach to extract acronyms and their definitions from a large text collection. The main contribution of this study has been to show the usefulness of statistical information for recognizing acronyms in large text collections. The proposed method combined with a letter matching algorithm achieved 78% precision and 85% recall on the evaluation corpus with 4,212 acronym-definition pairs.</Paragraph>
    <Paragraph position="1"> A future direction of this study would be to incorporate other types of relations expressed with parenthesis such as synonym, paraphrase, etc. Although this study dealt with the acronym-definition relation only, modelling these relations will also contribute to the accuracy of the acronym recognition, establishing a methodology to distinguish the acronym-definition relation from other types of relations.</Paragraph>
  </Section>
class="xml-element"></Paper>