<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-2042">
  <Title>Understanding &amp;quot;Each Other&amp;quot;</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Although there is widespread agreement that inference is an essential component of natural language processing, little work has been done so far on whether existing automated reasoning systems such as theorem provers and model builders could be fruitfully put to work in the area of natural language interpretation.</Paragraph>
    <Paragraph position="1"> In this paper, we focus on the inference problems raised by the reciprocal expression each other and show that model generation provides an adequate tool for modeling them.</Paragraph>
    <Paragraph position="2"> The paper is structured as follows. Section 3 discusses the meaning of reciprocal statements and proposes a formal semantics for each other.</Paragraph>
    <Paragraph position="3"> Section 2 shows how model generation can be used to provide this semantics with a computational interpretation. Section 4 compares our approach with the account of reciprocals which inspired it in the first place namely, (Dalrymple et al., 1998). Section 5 concludes with pointers for further research.</Paragraph>
  </Section>
class="xml-element"></Paper>