<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0902">
  <Title>Local Semantics in the Interpretation of Temporal Expressions</Title>
  <Section position="8" start_page="14" end_page="14" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have argued that, in the context of interpreting temporal expressions, there is value in identifying a level of semantic representation that corresponds to the meaning of these expressions outside of any particular document context. This idea is not in itself new, and many existing systems appear to make use of such representations.</Paragraph>
    <Paragraph position="1"> However, we have proposed that this level of representation be made explicit; and by providing an encoding of this level of representation that is an extension of the existing TIMEX2 annotations in terms of element attributes and their values, we make it possible to assess the performance of systems with respect to intermediate values, final values, or both, using standard evaluation tools.</Paragraph>
    <Paragraph position="2"> We have developed the representation described here on the basis of the set of 265 examples provided in the TIMEX2 guidelines (Ferro et al., 2005), and this set of annotated examples is available to the community.6 The approach described here is implemented in DANTE, a text processing system which produces normalised values for all TIMEXs found in a document. The recognition component of the system, which constructs the intermediate representations described here, is implemented via just over 200 rules written in the JAPE language:7 time expressions are thus recognised using finite state patterns, but we then apply a syntactic check, using the Connexor parser, to ensure that we have identified the full extent of each temporal expression, appropriately extending the extent when this is not the case.</Paragraph>
    <Paragraph position="3">  ham et al., 2002).</Paragraph>
    <Paragraph position="4"> We are currently testing this representation and its means of derivation against the data from the 2004 TERN competition. Our results are broadly comparable to those achieved by other systems (for example, Chronos or TempEx), though they can not be compared directly since the reported evaluations at the TERN competition use data which are not public and therefore not available to us.</Paragraph>
  </Section>
class="xml-element"></Paper>