<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1161">
  <Title>Acquisition of Semantic Classes for Adjectives from Distributional Evidence</Title>
  <Section position="6" start_page="35" end_page="35" type="concl">
    <SectionTitle>
5 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> In this paper we have pursued a line of research that seeks to induce semantic classes for adjectives from distributional evidence. Our current results indicate that it is possible, at least for Catalan. We believe that the approach could be straightforwardly extended to other Indoeuropean languages, such as Spanish, German or English.</Paragraph>
    <Paragraph position="1"> The resulting clusters largely correspond to the targeted classes in both parameters: unary vs. binary on the one hand, and basic-property vs. eventcomponent vs. object-component on the other. This is a remarkable result considering (a) that the human judges based their decisions on semantic criteria, whereas the features used corresponded to shallow distributional evidence, and (b) that we used an unsupervised technique. We have shown that for a part of speech with a limited syntactic distribution such as adjectives, this kind of information is enough to achieve a broad semantic classification.</Paragraph>
    <Paragraph position="2"> Our results also indicate that a semantic classification based on syntactic distribution is superior to one based on morphological class, mostly due to cases where the adjective has undergone diachronic change in meaning.</Paragraph>
    <Paragraph position="3"> However, there is a class that is not well identified: event adjectives. The clustering only identifies those that are binary, thus simply overlapping with the first parameter. The remaining event adjectives seem to behave like basic ones.</Paragraph>
    <Paragraph position="4"> Therefore, the first task in future work will be to review the definition and characterisation of this class. Also, as the present analysis is based on a small sample of manually annotated adjectives, we intend to obtain a larger Gold Standard, in order to establish statistically more reliable results. This will also allow further analysis of the data, e.g. to check to what extent errors in the clustering results correspond to disagreement between human judges; or how far from the centroid are objects for which judges disagree. Further experiments with alternative modelling strategies and clustering algorithms should be also performed, so that a global analysis of the approach can be made.</Paragraph>
    <Paragraph position="5"> We would also like to investigate what are the limits of adjective classification using only shallow distributional features, and what kinds of information would be adequate to enrich the modelling.</Paragraph>
    <Paragraph position="6"> Last but not least, we have to work on the definition of polysemy within our task, so that we can achieve significant agreement scores among judges and integrate this parameter in the experiment.</Paragraph>
  </Section>
class="xml-element"></Paper>