<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-4009">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics An Intermediate Representation for the Interpretation of Temporal Expressions</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Relation to Existing Work
</SectionTitle>
    <Paragraph position="0"> The most detailed system description in the published literature is that of the Chronos system from ITC-IRST (Negri and Marseglia, 2005). This system uses a large set of hand-crafted rules, and separates the recognition of temporal expressions from their interpretation. The ATEL system developed by the Center for Spoken Language Research (CSLR) at University of Colorado (see (Hacioglu et al., 2005)) uses SVM classifiers to detect temporal expressions. Alias-i's LingPipe also reported results for extraction, but not interpretation, of temporal expressions at TERN 2004.</Paragraph>
    <Paragraph position="1"> In contrast to this collection of work, which comes at the problem from a now-traditional information extraction perspective, there is also of course an extensive prior literature on the semantic of temporal expressions. Some more recent work attempts to bridge the gap between these two related enterprises; see, for example, Hobbs and Pan (2004).</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="34" type="metho">
    <SectionTitle>
3 The Underlying Model
</SectionTitle>
    <Paragraph position="0"> We describe briefly here our underlying conceptual model; a more detailed description is provided in (Dale and Mazur, 2006).</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1 Processes
</SectionTitle>
      <Paragraph position="0"> We take the ultimate goal of the interpretation of temporal expressions to be that of computing, for each temporal expression in a text, the point in time or duration that is referred to by that expression. We distinguish two stages of processing: Recognition: the process of identifying a temporal expression in text, and determining its extent. null Interpretation: given a recognised temporal expression, the process of computing the value of the point in time or duration referred to by that expression.</Paragraph>
      <Paragraph position="1"> In practice, the processes involved in determining the extent of a temporal expression are likely to make use of lexical and phrasal knowledge that mean that some of the semantics of the expression can already be computed. For example, in 2DANTE stands for Detection and Normalisation of Temporal Expressions.</Paragraph>
      <Paragraph position="2"> order to identify that an expression refers to a day of the week, we will in many circumstances need to recognize whether one of the specific expressions {Monday, Tuesday, ... Sunday} has been used; but once we have recognised that a specific form has been used, we have effectively computed the semantics of that part of the expression.</Paragraph>
      <Paragraph position="3"> To maintain a strong separation between recognition and interpretation, one could simply recompute this partial information in the interpretation phase; this would, of course, involve redundancy.</Paragraph>
      <Paragraph position="4"> However, we take the view that the computation of partial semantics in the first step should not be seen as violating the strong separation; rather, we distinguish the two steps of the process in terms of the extent to which they make use of contextual information in computing values. Then, recognition is that phase which makes use only of expressioninternal information and preposition which precedes the expression in question; and interpretation is that phase which makes use of arbitrarily more complex knowledge sources and wider document context. In this way, we motivate an intermediate form of representation that represents a 'context-free' semantics of the expression.</Paragraph>
      <Paragraph position="5"> The role of the recognition process is then to compute as much of the semantic content of a temporal expression as can be determined on the basis of the expression itself, producing an intermediate partial representation of the semantics. The role of the interpretation process is to 'fill in' any gaps in this representation by making use of information derived from the context.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="34" type="sub_section">
      <SectionTitle>
3.2 Data Types
</SectionTitle>
      <Paragraph position="0"> We view the temporal world as consisting of two basic types of entities, these being points in time and durations; each of these has an internal hierarchical structure. It is convenient to represent these as feature structures like the following:3  Our choice of attribute-value matrices is not accidental; in particular, some of the operations we want to carry out on the interpretations of both partial and complete temporal expressions can be conveniently expressed via unification, and this representation is a very natural one for such operations. null This same representation can be used to indicate the interpretation of a temporal expression at various stages of processing, as outlined below. In particular, note that temporal expressions differ in their explicitness, i.e. the extent to which the interpretation of the expression is explicitly encoded in the temporal expression; they also differ in their granularity, i.e. the smallest temporal unit used in defining that point in time or duration. So, for example, in a temporal reference like November 11th, interpretation requires us to make explicit some information that is not present (that is, the year); but it does not require us to provide a time, since this is not required for the granularity of the expression.</Paragraph>
      <Paragraph position="1"> In our attribute-value matrix representation, we use a special NULL value to indicate granularities that are not required in providing a full interpretation; information that is not explicitly provided, on the other hand, is simply absent from the representation, but may be added to the structure during later stages of interpretation. So, in the case of an expression like November 11th, the recognition process may construct a partial interpretation of the following form:  The representation thus very easily accommodates relative underspecification, and the potential for further specification by means of unification, although our implementation also makes use of other operations applied to these structures.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="34" end_page="35" type="metho">
    <SectionTitle>
4 Implementation
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="34" end_page="35" type="sub_section">
      <SectionTitle>
4.1 Data Structures
</SectionTitle>
      <Paragraph position="0"> We could implement the model above directly in terms of recursive attribute-value structures; however, for our present purposes, it turns out to be simpler to implement these structures using a string-based notation that is deliberately consistent with the representations for values used in the TIMEX2 standard (Ferro et al., 2005). In that notation, a time and date value is expressed using the ISO standard; uppercase Xs are used to indicate parts of the expression for which interpretation is not available, and elements that should not receive a value are left null (in the same sense as our NULL value above). So, for example, in a context where we have no way of ascertaining the century being referred to, the TIMEX2 representation of the value of the underlined temporal expression in the sentence We all had a great time in the '60s is simply VAL=&amp;quot;XX6&amp;quot;.</Paragraph>
      <Paragraph position="1"> We augment this representation in a number of ways to allow us to represent intermediate values generated during the recognition process; these extensions to the representation then serve as means of indicating to the interpretation process what operations need to be carried out.</Paragraph>
      <Paragraph position="2">  We use lowercase xs to indicate values that the interpretation process is required to seek a value for; and by analogy, we use a lowercase t rather than an uppercase T as the date-time delimiter in the structure to indicate when the recogniser is not able to determine whether the time is am or pm.</Paragraph>
      <Paragraph position="3"> This is demonstrated in the following examples; T-VAL is the attribute we use for intermediate TIMEX values produced by the recognition process. null  (5) a. We'll see you in November.</Paragraph>
      <Paragraph position="4"> b. T-VAL=&amp;quot;xxxx-11&amp;quot; (6) a. I expect to see you at half past eight.</Paragraph>
      <Paragraph position="5"> b. T-VAL=&amp;quot;xxxx-xx-xxt08:59&amp;quot; (7) a. I saw him back in '69.</Paragraph>
      <Paragraph position="6"> b. T-VAL=&amp;quot;xx69&amp;quot; (8) a. I saw him back in the '60s.</Paragraph>
      <Paragraph position="7"> b. TVAL=&amp;quot;xx6&amp;quot;  To handle the partial interpretation of relative date and time expressions at the recognition stage, we  use two extensions to the notation. The first provides for simple arithmetic over interpretations, when combined with a reference date determined from the context:  (9) a. We'll see you tomorrow.</Paragraph>
      <Paragraph position="8"> b. T-VAL=&amp;quot;+0000-00-01&amp;quot; (10) a. We saw him last year.</Paragraph>
      <Paragraph position="9"> b. T-VAL=&amp;quot;-0001&amp;quot;  The second provides for expressions where a more complex computation is required in order to determine the specific date or time in question:  (11) a. We'll see him next Thursday.</Paragraph>
      <Paragraph position="10"> b. T-VAL=&amp;quot;&gt;D4&amp;quot; (12) a. We saw him last November.</Paragraph>
      <Paragraph position="11"> b. T-VAL=&amp;quot;&lt;M11&amp;quot;</Paragraph>
    </Section>
    <Section position="2" start_page="35" end_page="35" type="sub_section">
      <SectionTitle>
4.2 Processes
</SectionTitle>
      <Paragraph position="0"> For the recognition process, we use a large collection of rules written in the JAPE pattern-matching language provided within GATE (see (Cunningham et al., 2002)). These return intermediate values of the forms described in the previous section.</Paragraph>
      <Paragraph position="1"> Obviously other approaches to recognizing temporal expressions and producing their intermediate values could be used; in DANTE, there is also a subsequent check carried out by a dependency parser to ensure that we have captured the full extent of the temporal expression.</Paragraph>
      <Paragraph position="2"> DANTE's interpretation process then does the following. First it determines if the candidate temporal expression identified by the recogniser is indeed a temporal expression; this is to deal with cases where a particular word or phrase annotated by the recognizer (such as time) can have both temporal or non-temporal interpretations. Then, for each candidate that really is a temporal expression, it computes the interpretation of that temporal expression.</Paragraph>
      <Paragraph position="3"> This second step involves different operations depending on the type of the intermediate value: * Underspecified values like xxxx-11 are combined with the reference date derived from the document context, with temporal directionality (i.e., is this date in the future or in the past?) being determined using tense information from the host clause.</Paragraph>
      <Paragraph position="4"> * Relative values like +0001 are combined with the reference date in the obvious manner. null * Relative values like &gt;D4 and &lt;M11 make use of special purpose routines that know about arithmetic for days and months, so that the correct behaviour is observed.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>