<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1055">
  <Title>Classifying Semantic Relations in Bioscience Texts</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have addressed the problem of distinguishing between several different relations that can hold between two semantic entities, a difficult and important task in natural language understanding.</Paragraph>
    <Paragraph position="1"> We have presented five graphical models and a neural network for the tasks of semantic relation classification and role extraction from bioscience text. The methods proposed yield quite promising results. We also discussed the strengths and weaknesses of the discriminative and generative  Sent.&amp;quot; the numbers of sentences used for training and testing and in the last column the classification accuracies for each relation. The total accuracy for this case is 74.9%. approaches and the use of a lexical hierarchy.</Paragraph>
    <Paragraph position="2"> Because there is no existing gold-standard for this problem, we have developed the relation definitions of Table 1; this however may not be an exhaustive list. In the future we plan to assess additional relation types. It is unclear at this time if this approach will work on other types of text; the technical nature of bioscience text may lend itself well to this type of analysis.</Paragraph>
    <Paragraph position="3"> Acknowledgements We thank Kaichi Sung for her work on the relation labeling and Chris Manning for helpful suggestions. This research was supported by a grant from the ARDA AQUAINT program, NSF DBI-0317510, and a gift from Genentech.</Paragraph>
  </Section>
class="xml-element"></Paper>