<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-1011">
  <Title>Learning and Application of Differential Grammars</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper, we explore the concept of a Differential Grammar and apply it to the problem of grammar checking - in the sense that it is used on the box your WYSIWYG word processor came in! A Differential Grammar is not a grammar in the traditional ruleoriented sense, and although it is lexically-focussed it doesn't really have a concept of a rule at all, but is somewhat more specialized, and extremely simple. We introduce a simple statistical preclassification, which we use to define a modified Ngram environment for each member of a confusion class, and then adjust the size of our environment until a pre-determined significance level or diameter is reached.</Paragraph>
    <Paragraph position="1"> We also demonstrate several approaches to the automated generation of the confusion classes.</Paragraph>
    <Paragraph position="2"> The structure of the paper is as follows: we introduce Differential Grammars and motivate them in terms of grammar checking, we discuss the acquisition, efficiency and significance issues, we present an improved user interface for grammar checkers, and we demonstrate the improvement achieved by Differential Grammar based checkers compared with commercial products. Finally, we discuss other experiments relating to automated acquisition of differential grammars.</Paragraph>
  </Section>
class="xml-element"></Paper>