<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1096">
  <Title>Wordformand class-based prediction of the components of German nominal compounds in an AAC system</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> The main result concerning German compound prediction that was reported in this paper pertains to the introduction of class-based modifier-head bigrams to enhance head prediction.</Paragraph>
    <Paragraph position="1"> We presented a procedure to cluster nominal wordforms into semantic classes and to extract class-based modifier-head bigrams, and then a model to calculate the class-based probability of candidate heads using these bigrams.</Paragraph>
    <Paragraph position="2"> While we evaluated our system in the context of the AAC word prediction task, we believe that the class-based prediction model we proposed could be extended to any other domain in which n-gram-based compound prediction must be performed. The addition of class-based head prediction to the split compound model of Baroni et al. (2002) leads to an improvement in head prediction (from a ksr of 48.8% to a ksr of 51.2%). This translates into an improvement of 1.3% in whole compound prediction (from 48.8% to 50.1%). Overall, the split compound model with class bigrams led to an improvement of more than 15% over a no split compound baseline model.</Paragraph>
    <Paragraph position="3"> This result was presented in the context of the AAC word prediction task, but we believe that the class-based prediction model we proposed could be extended to any other domain in which n-gram-based compound prediction must be performed.</Paragraph>
    <Paragraph position="4"> While the results we report are encouraging, the improvement obtained with the addition of the class-based model is hardly dramatic. It is clear that further work in this area is required.</Paragraph>
    <Paragraph position="5"> In particular, we plan to experiment with different measures of association to determine the degree of relatedness of words, and with alternative clustering techniques.</Paragraph>
    <Paragraph position="6"> Moreover, we hope to improve the overall performance of the compound predictor by resorting to a better interpolation strategy than the uniform weight assignment model we are currently using.</Paragraph>
    <Paragraph position="7"> We also reported results obtained with a preliminary model in which split compound prediction is integrated with simple noun prediction. This model outperforms the baseline model without compound prediction, but only of about 1% ksr. Clearly, further work in this area is also necessary. In particular, as suggested by a reviewer, we will try to exploit morpho-syntactic differences between simple nouns and modifiers to help distinguishing between the two types.</Paragraph>
  </Section>
class="xml-element"></Paper>