<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-2011">
  <Title>Towards an Optimal Lexicalization in a Natural-Sounding Portable Natural Language Generator for Dialog Systems</Title>
  <Section position="4" start_page="64" end_page="64" type="relat">
    <SectionTitle>
3 Related Work
</SectionTitle>
    <Paragraph position="0"> To date, only a limited amount of research has dealt with deep linguistically-based natural language generation for dialog systems. Theune (2003) presents an extensive overview of different NLG methods and systems. A number of stochastic-based generation efforts have been undertaken in recent years. These generators generally consist of an architecture similar to ours, in which first a set of possible candidates is constructed, followed by a decision process to choose the most appropriate output. Some examples are the Nitrogen system (Langkilde and Knight, 1998) and the SPoT trainable sentence planner (Walker et al., 2002).</Paragraph>
  </Section>
class="xml-element"></Paper>