<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1034">
  <Title>Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems</Title>
  <Section position="3" start_page="0" end_page="265" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> One obstacle to the widespread deployment of spoken dialogue systems is the cost involved withhand-craftingthespoken languagegeneration module. Spoken language generation requires a dictionary of mappings between semantic representations of concepts the system wants to express and realizations of those concepts. Dictionary creation is a costly process: an automatic method for creating them would make dialogue technology more scalable. A secondary benefit is that a learned dictionary may produce more natural and colloquial utterances.</Paragraph>
    <Paragraph position="1"> We propose a novel method for mining user reviews to automatically acquire a domain specific generation dictionary for information presentation in a dialogue system. Our hypothesis is that reviews that provide individual ratings for various distinguished attributes of review entities can be used to map review sentences to a semantic rep-An example user review (we8there.com)  The best Spanish food in New York. I am from Spain and I had my 28th birthday there and we all had a great time. Salud! | Review commentafter named entity recognition The best {NE=foodtype, string=Spanish}{NE=food, string=food, rating=5} in {NE=location, string=New  generation dictionary mapping.</Paragraph>
    <Paragraph position="2"> resentation. Figure 1 shows a user review in the restaurant domain, where we hypothesize that the user rating food=5 indicates that the semantic representation for the sentence &amp;quot;The best Spanish food in New York&amp;quot; includes the relation 'RESTAURANT has foodquality=5.' We apply the method to extract 451 mappings from restaurant reviews. Experimental analyses show that the mappings learned cover most of the domainontology,and providegoodlinguisticvariation. A subjective user evaluation indicates that the consistency between the semantic representations and the learned realizations is high and that the naturalness of the realizations is significantly higher than a hand-crafted baseline.</Paragraph>
    <Paragraph position="3">  Section 2 provides a step-by-step description of the method. Sections 3 and 4 present the evaluation results. Section 5 covers related work. Section 6 summarizes and discusses future work.</Paragraph>
  </Section>
class="xml-element"></Paper>