<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1053">
  <Title>STATISTICAL LANGUAGE PROCESSING USING HIDDEN UNDERSTANDING MODELS</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Hidden understanding models are an innovative application of statistical mechanisms that, given a string of words, determines the most likely meaning for the string. The overall approach represents a substantial departure from traditional approaches by replacing hand-crafted grammars and rules with statistical models that are automatically learned from examples.</Paragraph>
    <Paragraph position="1"> Advantages of tiffs approach include potential improvements in both robustness and portability of natural language systems.</Paragraph>
    <Paragraph position="2"> Hidden understanding models were motivated by techniques that have been extremely successful in speech recognition, especially hidden Markov Models \[Baum, 72\]. Related techniques have previously been applied to the problem of segmenting a sentence into a sequence of concept relations \[Pieraccini et aL, 91\].</Paragraph>
    <Paragraph position="3"> However, because of differences between language understanding and speech recognition, significant changes are required in the speech recognition methodology. Unlike speech, where each phoneme results in a local sequence of spectra, the relation between the meaning of a sentence and the sequence of words is not a simple linear sequential model. Language is inherently nested, with subgroups of concepts within other concepts.</Paragraph>
    <Paragraph position="4"> A statistical system for understanding language must take this and other differences into account in its overall design. In principle, we have the following requirements for a hidden understanding system: A notational system for expressing meanings.</Paragraph>
    <Paragraph position="5"> A statistical model that is capable of representing meanings and the association between meanings and words.</Paragraph>
    <Paragraph position="6"> An automatic training program which, given pairs of meanings and word sequences, can estimate the parameters of a statistical model.</Paragraph>
    <Paragraph position="7"> An understanding program that can search the statistical model to fred the most likely meaning given a word sequence.</Paragraph>
    <Paragraph position="8"> &amp;quot;J training \[/ m eanin$ sentences 1&amp;quot;- program ~ expressions  system.</Paragraph>
    <Paragraph position="9"> Below, we describe solutions for each of these requirements, and report on initial experiments with hidden understanding models.</Paragraph>
  </Section>
class="xml-element"></Paper>