<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1024">
  <Title>Independence Assumptions Considered Harmful</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper, we present an empirical argument in favor of a certain approach to statistical natural language modeling: we advocate statistical natural language models that account for the interactions between the explanatory statistical variables, rather than relying on independence a~ssumptions. Such models are able to perform prediction on the basis of estimated probability distributions that are properly conditioned on the combinations of the individual values of the explanatory variables.</Paragraph>
    <Paragraph position="1"> After describing one type of statistical model that is particularly well-suited to modeling natural language data, called a loglinear model, we present einpirical evidence fi'om a series of experiments on different ambiguity resolution tasks that show that the performance of the loglinear models outranks the performance of other models described in the literature that a~ssume independence between the explanatory variables.</Paragraph>
  </Section>
class="xml-element"></Paper>