<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1003">
  <Title>Event-building through Role-filling and Anaphora Resolution</Title>
  <Section position="2" start_page="0" end_page="18" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The computational linguistics literature includes a wide variety of ideas about how to represent events in as much detail as is required for reasoning about their implications. Less has been written about how to use information in text to incrementally build those event representations as discourse progresses, especially when the identification of event participants and other details is dispersed across a number of structures. We will be concerned here with providing a representational framework for this incremental event-building, and with using that representation to examine the ways in which reference to the internal structure of events contributes to discourse cohesion. That is, we will be interested both in the process of gleaning fully-specified event descriptions from continuous text, and in showing how individual elements of an event's internal structure can behave anaphorically.</Paragraph>
    <Paragraph position="1"> Examples of the kinds of linkages that must be dealt with in building representations of events from text follow:  la) He was believed Co be a liar.</Paragraph>
    <Paragraph position="2"> b) We promised him to be truthful.</Paragraph>
    <Paragraph position="3"> c) He tried to keep his mouth shut.</Paragraph>
    <Paragraph position="4"> 2a) Joe gave Pete a book to read.</Paragraph>
    <Paragraph position="5"> b) Joe gave Pete a book to impress him.</Paragraph>
    <Paragraph position="6"> c) Joe asked Pete for a book to read.</Paragraph>
    <Paragraph position="7"> d) I asked Joe for a book to impress Sam.</Paragraph>
    <Paragraph position="8"> e) Joe gave Pete the message to save his skin.</Paragraph>
    <Paragraph position="9"> 3a) Joe told Pete that to err is human.</Paragraph>
    <Paragraph position="10"> b) He told us that to quit eould be silly.</Paragraph>
    <Paragraph position="11"> 4a) GM will broaden collaboration with  Lotus to make a new car.</Paragraph>
    <Paragraph position="12"> b) Mary thought that an argument with herself would be entertaining.</Paragraph>
    <Paragraph position="13"> c) Mary thought that a conference with himself would make John look silly.</Paragraph>
    <Paragraph position="14"> The examples in (1) are familiar cases of syntactically obligatory control; we will consider their behavior to be straightforwardly and locally resolved. The sentences of (2) show infinitival relatives, purpose, and 'in-order-to' clauses in which control of the infinitive (and hence of its implicit subject) is sometimes clear, sometimes ambiguous. In (3), a subject infinitival phrase receives an unavoidably generic reading in one case and a non-generic but ambiguous reading in the other. Finally, the examples of (4) indicate that nominalizations of events also have roles whose reference must be determined, and whose existence and identity has consequences for subsequent discourse.</Paragraph>
    <Paragraph position="15"> Aside from the sentences in (1), in which control is unambiguously sorted out within the sentence on the basis of verb type, all the examples above can  be paraphrased with equivalent multi-sentence constructions in which the facts of referent-assignment are identical. Even more extended discourses, including dialogues such as that in (5), show the influence of an instantiated situation or event over the assignment of referents to entities introduced later in the discourse.</Paragraph>
    <Paragraph position="16"> 5) A: John has been hobbling around for two weeks with a sprained ankle.</Paragraph>
    <Paragraph position="17"> B: So what did the nurse say yesterday? A: She said that it would not be smart to run so soon after injuring himself.</Paragraph>
    <Paragraph position="18"> (adapted from Nishigauchi's 48, cited as a modification of Chao's 28) The distribution of event participants across multi-sentence discourses is sufficient to lay to rest any idea that the linkage is syntactically governed, even though the entities which provide cohesion in these examples are arguments which are typically bound syntactically. That is, it seems that initially unfilled thematic roles play a part in tying one sentence to the next. Event roles left unfilled after the operation of local syntactic processing are apparently still 'active', in some sense, and they appear to be able to attract participants from external structures to fill them. Carlson and Tanenhaus (1988) provide psycholinguistic evidence that this is indeed the case; open thematic roles do appear to be effective as cohesion devices. 1 Previous theories about how open roles become filled (mostly intra-sententially) have been based on notions ranging from strictly syntactic to more pragmatic, knowledge-based approaches. Obviously wherever we do have what appears to be invariant and obligatory control, we want to exploit a syntactic explanation. However, these cases 1Whether it is just thematic roles, or those plus certain types of highly predictable adjuncts, or a wide variety of other types of slots which can provide the type of linking we are talking about is still an open question. We do assume that for each event we will encode not only THAT it expects certain arguments to be filled, but HOW it expects them to be filled; for instance it should be perceived that the noun 'salesman' is a highly suitable Agent for a sale event. We may need to know about more than that. In particular, we may require metonymical devices that make discourses like the following possible.</Paragraph>
    <Paragraph position="19"> I had a hard time shopping.</Paragraph>
    <Paragraph position="20"> First, the parking lot was all full ....</Paragraph>
    <Paragraph position="21"> Coherence in this example dearly depends on being able to associate 'the parking lot' with 'store' and 'store' with the Location of the 'shopping' event. This extension is no different in kind, however, from the core of what we are proposing here.</Paragraph>
    <Paragraph position="22"> do not account for much of the ground that we need to cover. As the examples above show, even the syntactic position PRO often defies straightforward control assignment, and in the case of nominal references to events, Williams' (1985) arguments against a strictly syntactic account of referent-assignment are convincing. Of course, there are no syntactic means for linking arguments with event descriptions intersententially. Appeals to underlying thematic role notions and/or more pragmatically governed operators then seem to hold more promise for the kinds of situations we are describing. null Given their currency above and below the sentence level, and the fact that they seem to be sensitive to both syntactic and pragmatic constraints, the behavior of unfilled event roles will best be explained at the discourse level. Like other discourse anaphoric elements, open roles can not only receive their reference from distant structures, but they also seem to be used productively to create links between linguistic structures and to extend focus in both forward and backward directions.</Paragraph>
    <Paragraph position="23"> To machine-build representations of events whose essential components are dispersed across multiple structures, two key ingredients are necessary. First, the system must have knowledge about events and their expected participants and other characteristics. Given this, one can make predictions about the expectancy of arguments and the underlying properties they should hold. The second ingredient required is a means for assessing the mutual accessibility of discourse entities. As has been pointed out by various researchers, sentential structure, thematic relationships, and discourse configurations all may play a part in determining which entities must, might, and cannot be associated with others, and a discourse framework must make it possible to take all these factors into account in assigning reference and building representations of events.</Paragraph>
    <Paragraph position="24"> Our intent in this paper is to provide a prototype model of event building which is effective across clauses, both intra- and inter-sententially. We will incorporate into this representation of events a means for assessing accessibility of events and event participants for anaphoric reference, and we will use the representation to examine the anaphoric behavior of open roles.</Paragraph>
    <Paragraph position="25"> Event-Building Representation: We have chosen DRT as an overall representation scheme, though we will be modifying it to some extent.</Paragraph>
    <Paragraph position="26"> DRT has been designed to perform a variety of  tasks, including proper placement of individual events in an overall discourse representation and making it possible to indicate which event entities are available for future anaphoric referencing and what constraints hold over those entities. A typical DR for a simple sentence is given in (6). The sentence, 'John gave Bill a dollar' is designated by the variable E1 and has associated with it a predicate calculus statement that contains the predicate, give, and argument variables V1, V2, and V3. The give event specification and other constraints, again in predicate calculus form, are contained in the lower portion of the DR. In the top half of the DR, any entities, including events, which are available for subsequent anaphoric referencing are listed by their variable names.</Paragraph>
    <Paragraph position="28"> Our representation departs in some ways from the way in which the binding of anaphors is usually shown in DRT. In versions of DRT with realtime processing, whenever an NP is being processed, two things can happen: i) either the NP can be linked with a previously occurring NP and become anaphorically bound to it, or ii) a new referent can be generated for the NP and posted when no antecedent can be found. For our purposes, it is convenient to include in the DR an extra tier which contains items which have not yet found a referent. ~ To designate the three parts of our DRs, we will use the following tier labels:  For processing purposes, we will not attempt to immediately bind anaphors as they are encountered in sentences, beyond what we can get for free from syntactic analysis. Rather, we will initiate a two-stage process, with the first DR having unbound anaphors and the second attempting representation of binding. In the first representation, we will</Paragraph>
  </Section>
class="xml-element"></Paper>