<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1051">
  <Title>Automatic learning of textual entailments with cross-pair similarities</Title>
  <Section position="9" start_page="407" end_page="407" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have presented a model for the automatic learning of rewrite rules for textual entailments from examples. For this purpose, we devised a novel powerful kernel based on cross-pair similarities. We experimented with such kernel using Support Vector Machines on the RTE test sets. The results show that (1) learning entailments from positive and negative examples is a viable approach and (2) our model based on kernel methods is highly accurate and improves on the current state-of-the-art entailment systems.</Paragraph>
    <Paragraph position="1"> In the future, we would like to study approaches to improve the computational complexity of our kernel function and to design approximated versions that are valid Mercer's kernels.</Paragraph>
  </Section>
class="xml-element"></Paper>