<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1139">
  <Title>Stochastic Language Generation Using WIDL-expressions and its Application in Machine Translation and Summarization</Title>
  <Section position="9" start_page="1109" end_page="1111" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> The approach to sentence realization we advocate in this paper relies on WIDL-expressions, a formal language with convenient theoretical properties that can accommodate a wide range of generation scenarios. In the worst case, one can work with simple bags of words that encode no context  preferences (Soricut and Marcu, 2005). One can also work with bags of words and phrases that encode context preferences, a scenario that applies to current approaches in statistical machine translation (Section 5). And one can also encode context and ordering preferences typically used in summarization (Section 4).</Paragraph>
    <Paragraph position="1"> The generation engine we describe enables a tight coupling of content selection with sentence realization preferences. Its algorithm comes with theoretical guarantees about its optimality.</Paragraph>
    <Paragraph position="2"> Because the requirements for producing WIDL-expressions are minimal, our WIDL-based generation engine can be employed, with state-of-the-art results, in a variety of text-to-text applications.</Paragraph>
    <Paragraph position="3"> Acknowledgments This work was partially supported under the GALE program of the Defense Advanced Research Projects Agency, Contract No. HR0011-06-C-0022.</Paragraph>
  </Section>
class="xml-element"></Paper>