<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-1305">
  <Title>A Model for Processing Temporal References in Chinese</Title>
  <Section position="3" start_page="2" end_page="2" type="intro">
    <SectionTitle>
2 A Model for Temporal Relation
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="2" end_page="2" type="sub_section">
      <SectionTitle>
Discovery
2.1 Temporal Concept Frame
</SectionTitle>
      <Paragraph position="0"> In IE, it is impossible as well as impractical to extract all the information from an incoming document. For this reason, all IE systems are geared for specic application domains. The domain is determined by a pre-specied concept dictionary.</Paragraph>
      <Paragraph position="1"> Then a certain concept is triggered byseveral lexical items and activated in the specic linguistic contexts. Each concept denition contains a set of slots for the extracted information. In addition, it contains a set of enabling conditions which are constraints that must be satised in order for the concept to be activated. Due to its versatility, a frame structure is generally used to representconcepts (as shown in Figure 1).</Paragraph>
      <Paragraph position="2"> Slots in a temporal concept frame are divided into twotypes: activity-related and time-related.</Paragraph>
      <Paragraph position="3"> Activity-related slots provide the descriptions of objects and actions concerning the concept. For example, company predator, company target and purchase value are the attributes of the concept (Be, TAKEOVER). Meanwhile, time-related slots provide information related to when a concept begins or nishes, how long does it last and how does it relate to another concept, etc.</Paragraph>
      <Paragraph position="4"> referenced concept frame</Paragraph>
    </Section>
    <Section position="2" start_page="2" end_page="2" type="sub_section">
      <SectionTitle>
2.2 Temporal Relations
</SectionTitle>
      <Paragraph position="0"> The system is designed with two sets of temporal relations, namely absolute and relative relations.</Paragraph>
      <Paragraph position="1"> The role of absolute temporal relations is to position situation occurrences on a time axis. These relations depict the beginning and/or ending time bounds of an occurrence or its relevance to reference times, see TR(T) in Section 2.3. Absolute relations are organized by Time Line in the system, see Figure 2.</Paragraph>
      <Paragraph position="2"> r: t: d:absolute relation time parameter duration  lute relations in TICS In many cases, the time when an event takes place may not be known. But its relevance to another occurrence time is given. Relative temporal knowledge such as this is manifested by relative relations. Allen has proposed thirteen relations. The same is adopted in our system, see</Paragraph>
      <Paragraph position="4"> ) in Section 2.3. The relative relations are derived either directly from a sentence describing two situations, or indirectly from the absolute relationsof two individual situations. They areorganized by Relational Chains, as shown in Figure</Paragraph>
    </Section>
    <Section position="3" start_page="2" end_page="2" type="sub_section">
      <SectionTitle>
2.3 Temporal Model
</SectionTitle>
      <Paragraph position="0"> This section describes our temporal model for discovering relations from Chinese sentences.</Paragraph>
      <Paragraph position="1"> Suppose TR indicates a temporal relation, E indicates an event and T indicates time. The absolute and relative relations are symbolized as:</Paragraph>
      <Paragraph position="3"> tively. The sets of TRare:</Paragraph>
      <Paragraph position="5"/>
    </Section>
  </Section>
class="xml-element"></Paper>