<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1611">
  <Title>Discrete Optimization as an Alternative to Sequential Processing in NLG</Title>
  <Section position="6" start_page="22" end_page="22" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper we showed that the pipeline architecture in an NLG application can be successfully replaced with an integrated ILP-based model which is better suited to handling correlated generation decisions. To the best of our knowledge, linear programming has been used in an NLG related work only by [Althaus et al., 2004] to solve a single task of determining the order of discourse constituents. In a somewhat related context [Dras, 1999] used ILP to optimize the task of text paraphrasing, given global constraints such as text and sentence length, readibilty, etc.</Paragraph>
    <Paragraph position="1"> In contrast, in this work we use an ILP model to organize the entire process of generating the surface form from an underlying semantic representation, which involves an integration of different types of NLG tasks. Although in our system we use machine learning as the primary decision making mechanism, we believe that the ILP model can also be used with knowledge-based systems that observe the classification-oriented formulation of the NLG tasks.</Paragraph>
    <Paragraph position="2"> Finally, we are convinced that an adequate evaluation of an NLG system must at some stage go beyond the application of quantitative measures. Nevertheless, it is reasonable to expect that the improvement that we reached with the ILP system, especially the increase of the overall Phi score, must correlate to some extent with the quality improvement. To verify it we are currently proceeding with qualitative evaluation of the output from our system.</Paragraph>
    <Paragraph position="3"> Acknowledgements: The work presented here has been funded by the Klaus Tschira Foundation, Heidelberg, Germany. The first author receives a scholarship from KTF (09.001.2004).</Paragraph>
  </Section>
class="xml-element"></Paper>