<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1420">
  <Title>Building a semantically transparent corpus for the generation of referring expressions</Title>
  <Section position="4" start_page="131" end_page="131" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> Corpora can be an invaluable resource for NLG as long as the necessary contextual information and the conditions under which the texts in a corpus were produced are known. We believe that controlled and balanced experiments are needed for building semantically transparent resources, whose construction we have discussed. As shown in this paper, evaluation of algorithms against the number of gold standards obtained with such a corpus needs careful consideration.</Paragraph>
    <Paragraph position="1"> Evaluation of GRE - and NLG systems more generally - would benefit from more investigation of the differences between readers and producers. In future work, we intend to follow up with a reader-oriented experiment in which we test the speed and/or accuracy with which the output of different GRE algorithms is understood by subjects. The dependent variables here will be non-linguistic (perhaps involving subjects clicking on pictures of presumed target referents). This illustrates a more general issue in this area, namely that corpora should, in our view, only be a starting point, with which data of different kinds can be associated.</Paragraph>
  </Section>
class="xml-element"></Paper>