<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1137">
  <Title>Identification of Confusable Drug Names: A New Approach and Evaluation Methodology</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have investigated the problem of identifying confusable drug name pairs. The effectiveness of several word similarity measures was evaluated using a new recall-based evaluation methodology. We have proposed a new measure of orthographic similarity that outperforms several commonly used similarity measures when tested on a publicly available list of confusable drug names. On a test set containing solely sound-alike confusion pairs phonetic approaches, ALINE and EDITEX achieve the best results. Our results suggest that a linear combination of several measures benefits from the strengths of its components, and is likely to outperform any individual measure. Such a combined approach has the potential to provide the basis for automatic minimization of medication errors.</Paragraph>
    <Paragraph position="1"> The task of computing similarity between words is also important in other contexts. When an entered name does not exist in a bibliographic database, it is desirable to retrieve names that sound similar. Information retrieval systems may need to expand the search in cases where a typed query contains errors or variations in spelling. A related task of the identification of cognates arises in statistical machine translation. The techniques discussed in this paper may also be applicable in those areas.</Paragraph>
  </Section>
class="xml-element"></Paper>