<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0208">
  <Title>Temporal Discourse Models for Narrative Structure</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Temporal Discourse Models
</SectionTitle>
    <Paragraph position="0"> A TDM is a tree-structured syntactic model of global discourse structure, where temporal relations are used as surrogates for discourse relations, and where abstract events corresponding to entire discourses are introduced as nodes in the tree.</Paragraph>
    <Paragraph position="1"> In (1) the embedding nodes E0 and E1 were abstract, but textually mentioned events can also create embeddings, as in (2) (example from (Spejewski 1988)): We begin by illustrating the basic intuition. Consider discourse (1), from (Webber 1988): (2) a. Edmond made his own Christmas presents this year. b. First he dried a bunch of tomatoes in his oven. c. Then he made a booklet of recipes that use dried tomatoes. d. He scanned in the recipes from his gourmet magazines. e. He gave these gifts to his family.</Paragraph>
    <Paragraph position="2">  (1) a. John went into the florist shop. b. He had promised Mary some flowers.</Paragraph>
    <Paragraph position="3"> c. She said she wouldn't forgive him if he  forgot. d. So he picked out three red roses. The discourse structure of (1) can be represented by the tree, T1, shown below.</Paragraph>
    <Paragraph position="5"> Here E0 has children Ea, E1, and Ed, and E1 has children Eb and Ec. The nodes with alphabetic subscripts are events mentioned in the text, whereas nodes with numeric subscripts are abstract events, i.e., events that represent abstract discourse objects. A node X is a child of node Y iff X is temporally included in Y. In our scheme, events are represented as pairs of time points. So, E0 is an abstract node representing a top-level story, and E1 is an abstract node representing an embedded story. Note that the mentioned events are ordered left to right in text order for notational convenience, but no temporal ordering is directly represented in the tree. Since the nodes in this representation are at a semantic level, the tree structure is not necessarily isomorphic to a representation at the text level, although T1 happens to be isomorphic.</Paragraph>
    <Paragraph position="7"> Note that the partial ordering C can be extended using T and temporal closure axioms (Setzer and Gaizauskas 2001), (Verhagen 2004), so that in the case of &lt;T2, C2&gt;, we can infer, for example, that Eb &lt; Ed, Ed &lt; Ee, and so forth.</Paragraph>
    <Paragraph position="8"> In representing states, we take a conservative approach to the problems of ramification and change (McCarthy and Hayes 1969). This is the classic problem of recognizing when states (the effects of actions) change as a result of actions. Any tensed stative predicate will be represented as a node in the tree (progressives are here treated as stative). Consider an example like John walked home. He was feeling great.</Paragraph>
    <Paragraph position="9"> Here we represent the state of feeling great as being minimally a part of the event of walking, without committing to whether it extends before or after the event. While this is interpreted as an overloaded temporal inclusion in the TDM tree, a constraint is added to C indicating that this inclusion is minimal.</Paragraph>
    <Paragraph position="10"> This conservative approach results in logical incompleteness, however. For example, given the discourse Max entered the room. He was wearing a black shirt, the system will not know whether the shirt was worn after he entered the room. States are represented as bounded intervals, and participate in ordering relations with events in the tree. It is clear that in many cases, a state should persist throughout the interval spanning subsequent events. This is not captured by the current tree representation. Opposition structures of predicates and gating operations over properties can be expressed as constraints introduced by events, however, but at this stage of development, we have been interested in capturing a coarser temporal ordering representation, very robustly.</Paragraph>
    <Paragraph position="11"> We believe, however, that annotation using the minimal inclusion relation will allow us to reason about persistence heuristically in the future.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Prerequisites
</SectionTitle>
    <Paragraph position="0"> Prior work on temporal information extraction has been fairly extensive and is covered in (Mani et al.</Paragraph>
    <Paragraph position="1"> 2004). Recent research has developed the TimeML annotation scheme (Pustejovsky et al. 2002) (Pustejovsky et al. 2004), as well as a corpus of TimeML-annotated news stories (TimeBank 2004) and annotation tools that go along with it, such as the TANGO tool (Pustejovsky et al. 2003).</Paragraph>
    <Paragraph position="2"> TimeML flags tensed verbs, adjectives, and nominals that correspond to events and states, tagging instances of them with standard TimeML attributes, including the class of event (perception, reporting, aspectual, state, etc.), tense (past, present, future), grammatical aspect (perfective, progressive, or both), whether it is negated, any modal operators which govern it, and its cardinality if the event occurs more than once.</Paragraph>
    <Paragraph position="3"> Likewise, time expressions are flagged, and their values normalized, so that Thursday in He left on Thursday would get a resolved ISO time value depending on context (TIMEX2 2004). Finally, temporal relations between events and time expressions (e.g., that the leaving occurs during Thursday) are recorded by means of temporal links (TLINKs) that express Allen-style interval relations (Allen 1984).</Paragraph>
    <Paragraph position="4"> Several automatic tools have been developed in conjunction with TimeML, including event taggers (Pustejovsky et al. 2003), time expression taggers (Mani and Wilson 2000), and an exploratory link extractor (Mani et al. 2003).</Paragraph>
    <Paragraph position="5"> Temporal reasoning algorithms have also been developed, that apply transitivity axioms to expand the links using temporal closure algorithms (Setzer and Gaizauskas 2001), (Pustejovsky et al. 2003).</Paragraph>
    <Paragraph position="6"> However, TimeML is inadequate as a temporal model of discourse: it constructs no global representation of the narrative structure, instead annotating a complex graph that links primitive events and times.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 Related Frameworks
</SectionTitle>
    <Paragraph position="0"> Since the relations in TDMs involve temporal inclusion and temporal ordering, the mentioned events can naturally be mapped to other discourse representations used in computational linguistics.</Paragraph>
    <Paragraph position="1"> A TDM tree can be converted to a first-order temporal logic representation (where temporal ordering and inclusion operators are added) by expanding the properties of the nodes. These properties include any additional predications made explicitly about the event, e.g., information from thematic arguments and adjuncts. In other words, a full predicate argument representation, e.g., as might be found in the PropBank (Kingsbury and Palmer 2002), can be associated with each node.</Paragraph>
    <Paragraph position="2"> TDMs can also be mapped to Discourse Representation Structures (DRS) (which in turn can be mapped to a logical form). Since TDMs represent events as pairs of time points (which can be viewed as intervals), and DRT represents events as primitives, we can reintroduce time intervals based on the standard DRT approach (e [?] t for events, e O t for states, except for present tense states, where t [?] e).</Paragraph>
    <Paragraph position="3"> Consider an example from the Discourse  (3) a. A man entered the White Hart. b. He  was wearing a black jacket. c. Bill served him a beer.</Paragraph>
    <Paragraph position="4"> The TDM is &lt;T3, C3&gt; below, with internal properties of the nodes as shown:</Paragraph>
    <Paragraph position="6"> node.properties(Ea): enter(Ea, x, y), man(x), y= theWhiteHart, Ea &lt; n node.properties(Eb): PROG(wear(Eb, x1, y1)), black-jacket(y1), x1=x, Eb &lt; n, node.properties(Ec): serve(Ec, x2, y2, z), beer(z), x2=Bill, y2=x, Ec &lt; n From T3: Eb [?] Ea From C3: Ea &lt; Ec  The DRT representation is shown below (here we have created variables for the reference times): Note that we are by no means claiming that DRSs and TDMs are equivalent. TDMs are tree-structured and DRSs are not, and the inclusion relations involving our abstract events, i.e., Ea [?] E0 and Ec [?] E0, are not usually represented in DRT. Nevertheless, there are many similarities between TDMs and DRT which are worth examining for semantic and computational properties. Furthermore, SDRT (Asher and Lascarides 2003) extends DRT to include discourse relations. SDRT and RST both differ fundamentally from TDMs, since we dispense with rhetorical relations.</Paragraph>
    <Paragraph position="7"> It should be pointed out, nevertheless, that TDMs, as modeled so far, do not represent modality and intensional contexts in the tree structure. (However, information about modality and negation is stored in the nodes based on TimeML preprocessing). One way of addressing this issue is to handle lexically derived modal subordination (such as believe and want) by introducing embedded events, linked to the modal predicate by subordinating relations. For example, in the sentence John believed that Mary graduated from Harvard, the complement event is represented as a subtree linked by a lexical relation.</Paragraph>
    <Paragraph position="8"> DLTAG (Webber et al. 2004) is a model of discourse structure where explicit or implicit discourse markers relating only primitive discourse units. Unlike TDMs, where the nodes in the tree can contain embedded structures, DLTAG is a local model of discourse structure; it thus provides a set of binary relations, rather than a tree Like TDMs, however, DLTAG models discourse structure without postulating the existence of rhetorical relations in the discourse tree. Instead, the rhetorical relations appear as predicates in the semantic forms for discourse markers. In this respect, they differ from TDMs, which do not commit to specific rhetorical relations.</Paragraph>
    <Paragraph position="9"> Spejewski (1994) developed a tree-based model of the temporal structure of a sequence of sentences. Her approach is based on relations of temporal coordination and subordination, and is thus a major motivation for our own approach. However, her approach mixes both reference times and events in the same representation, so that the parent-child relation sometimes represents temporal anchoring, and at other times coordination. In the above example of John walked home. He was feeling great, her approach would represent the &amp;quot;reference time&amp;quot; of the state (of feeling great) as being part of the event of walking as well as part of the state, resulting in a graph rather than a strict tree. Note that our approach uses minimality.</Paragraph>
    <Paragraph position="10"> Ea, x, y , Eb, x1, y1, Ec, x2, y2, z,</Paragraph>
    <Paragraph position="12"> [?] Ea, t3 &lt; n, Ec [?] t3, Ea &lt; Ec (Hitzeman et al. 1995) developed a computational approach to distinguish various temporal threads in discourse. The idea here, based on the notion of temporal centering, is that there is one 'thread' that the discourse is currently following. Thus, in (1) above, each utterance is associated with exactly one of two threads: (i) going into the florist's shop and (ii) interacting with Mary. Hitzeman et al. prefer an utterance to continue a current thread which has the same tense or is semantically related to it, so that in (1) above, utterance d would continue the thread (i) above based on tense. In place of world knowledge, however, semantic distance between utterances is used, presumably based on lexical relationships.</Paragraph>
    <Paragraph position="13"> Whether such semantic similarity is effective is a matter for evaluation, which is not discussed in their paper. For example, it isn't clear what would rule out (1c) as continuing thread (i).</Paragraph>
    <Paragraph position="14"> While TDMs do not commit to rhetorical relations, our expectation is that they can be used as an intermediate representation for rhetorical parsing. Thus, when event A in a TDM temporally precedes its right sibling B, the rhetorical relation of Narration will typically be inferred. When B precedes is left sibling A, then Explanation will typically be inferred. When A temporally includes a child node B, then Elaboration is typically inferred, etc. TDMs are thus a useful shallow representation that can be a useful first step in deriving rhetorical relations; indeed, rhetorical relations may be implicit in the human annotation of such relations, e.g., when explicit discourse markers like &amp;quot;because&amp;quot; indicate a particular temporal order.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
5 Annotation Scheme
</SectionTitle>
    <Paragraph position="0"> The annotation scheme involves taking each document that has been preprocessed with time expressions and event tags (complying with TimeML) and then representing TDM parse trees and temporal ordering constraints (the latter also compliant with TimeML TLINKS).</Paragraph>
    <Paragraph position="1"> Each discourse begins with a root abstract node. As an annotation convention, (A1) in the absence of any overt or covert discourse markers or temporal adverbials, a tense shift will license the creation of an abstract node, with the event with the shifted tense being the leftmost daughter of the abstract node. The abstract node will then be inserted as the child of the immediately preceding text node. In addition, convention (A2) states that in the absence of temporal adverbials and overt or covert discourse markers, a stative event will always be placed as a child of the immediately preceding text event when the latter is non-stative. Further, convention (A3) states that when the previous event is stative, in the absence of temporal adverbials and explicit or implicit discourse markers, the stative event is a sibling of the previous stative (as in a scene-setting fragment of discourse).</Paragraph>
    <Paragraph position="2"> We expect that inter-annotator reliability on TDM trees will be quite high, given the transparent nature of the tree structure along with clear annotation conventions. The Appendices provide examples of annotation, to illustrate the simplicity of the scheme as well as potential problems.</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
6 Corpora
</SectionTitle>
    <Paragraph position="0"> We have begun annotating three corpora with Temporal Discourse Model information. The first is the Remedia corpus (remedia.com). There are 115 documents in total, grouped into four reading levels, all of which have been tagged by a human for time expressions in a separate project by Lisa Ferro at MITRE. Each document is short, about 237 words on average, and has a small number of questions after it for reading comprehension.</Paragraph>
    <Paragraph position="1"> The Brandeis Reading Corpus is a collection of 100 K-8 Reading Comprehension articles, mined from the web and categorized by level of comprehension difficulty. Articles range from 50-350 words in length. Complexity of the reading task is defined in terms of five basic classes of reading difficulty.</Paragraph>
    <Paragraph position="2"> The last is the Canadian Broadcasting Corporation (cbc4kids.ca). The materials are current-event stories aimed at an audience of 8year-old to 13-year-old students. The stories are short (average length around 450 words). More than a thousand articles are available. The CBC4Kids corpus is already annotated with POS and parse tree markup.</Paragraph>
  </Section>
class="xml-element"></Paper>