<?xml version="1.0" standalone="yes"?>
<Paper uid="E99-1007">
  <Title>Automatic Verb Classification Using Distributions of Grammatical Features</Title>
  <Section position="7" start_page="50" end_page="50" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have presented an in-depth case study, in which we apply machine learning techniques to automatically classify a set of verbs, based on distributional features extracted from a very large corpus. Results show that a small number of linguistically motivated grammatical features are sufficient to halve the error rate over chance. This leads us to conclude that corpus data is a usable repository of verb class information. On one hand, we observe that semantic properties of verb classes (such as causativity) may be usefully approximated through countable features. Even with some noise, lexical properties are reflected in the corpus robustly enough to positively contribute in classification. On the other hand, however, we remark that deep linguistic analysis cannot be eliminated. In our approach, it is embedded in the selection of the features to count. We also think that using linguistically motivated features makes the approach very effective and easily scalable: we report a 50% reduction in error rate, with only 4 features that are relatively straightforward to count.</Paragraph>
  </Section>
class="xml-element"></Paper>