<?xml version="1.0" standalone="yes"?>
<Paper uid="H91-1020">
  <Title>STOCHASTIC REPRESENTATION OF CONCEPTUAL STRUCTURE IN THE ATIS TASK</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The goal of a speech understanding system is generally that of translating a sequence of acoustic measurements of the speech signal into some form that represents the meaning conveyed by the sentence. One of the knowledge representation paradigms, known as semantic networks \[2\] establishes relations between conceptual entities using a graph structure. These concept relations, or linguistic cases, can be used to label different parts of a sentence in order to obtain its interpretation. The task itself defines the set of relevant cases. For instance, for the task of assigning the origin, the destination and the departure time of a flight, a convenient representation is in terms of the following set of cases:</Paragraph>
    <Paragraph position="2"> of a DUMMY case is useful for covering all the parts of the sentence that are not relevant to the task. A sentence like ! would like to fly from Boston to Chicago next Saturday night can be analyzed as:  * DUMMY: I would like to fly * ORIGIN: from Boston * DESTINATION: to Chicago * DEPARTURE_TIME: next Saturday night.</Paragraph>
    <Paragraph position="3">  Note that although the first phrase (I would like to fly) conveys important information, it is considered irrelevant to this particular task, and therefore assigned to the DUMMY case. The segmentation of a sentence into cases (conceptual segmentation) can be described by labeling each word in the sentence with the index of the case it expresses. In the example above, the conceptuM segmentation is represented by the following sequence of labels:</Paragraph>
    <Paragraph position="5"> In this paper we tackle the problem of decoding the words constituting the spoken sentence and the corresponding sequence of case labels, from the speech signal.</Paragraph>
  </Section>
class="xml-element"></Paper>