<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0901">
  <Title>Hiding a Semantic Hierarchy in a Markov Model</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
TOP
LOCA~ON ENTITY
LEc'E.FORM CAUSAL-AGENT
PERSON e~ ~ &amp;quot;~'~ BEEs ~m,,r~Z
WORKER
BEE WORKER FEMALE MALE
</SectionTitle>
    <Paragraph position="0"> formally define our stochastic model. Next we look at a number of ultimately unsuccessful attempts to modify the forward-backward algorithm to perform effective word-sense disambiguation of the training data. Despite these problems we did obtain some encouraging results which we present at the end of the paper.</Paragraph>
  </Section>
class="xml-element"></Paper>