<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-2026">
  <Title>Trainable Methods for Surface Natural Language Generation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> This paper presents three trainable systems for surface natural language generation (NLG). Surface NLG, for our purposes, consists of generating a grammatical natural language phrase that expresses the meaning of an input semantic representation.</Paragraph>
    <Paragraph position="1"> The systems take a &amp;quot;corpus-based&amp;quot; or &amp;quot;machinelearning&amp;quot; approach to surface NLG, and learn to generate phrases from semantic input by statistically analyzing examples of phrases and their corresponding semantic representations. The determination of the content in the semantic representation, or &amp;quot;deep&amp;quot; generation, is not discussed here. Instead, the systems assume that the input semantic representation is fixed and only deal with how to express it in natural language.</Paragraph>
    <Paragraph position="2"> This paper discusses previous approaches to surface NLG, and introduces three trainable systems for surface NLG, called NLG1, NLG2, and NLG3.</Paragraph>
    <Paragraph position="3"> Quantitative evaluation of experiments in the air travel domain will also be discussed.</Paragraph>
  </Section>
class="xml-element"></Paper>