<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-1311">
  <Title>Event Coreference for Information Extraction</Title>
  <Section position="3" start_page="75" end_page="76" type="metho">
    <SectionTitle>
2 LaSIE Overview
</SectionTitle>
    <Paragraph position="0"> The Large Scale Information Extraction system (LaSIE) has been designed as a general purpose IE research system, initially geared towards, but not 2While no extended study has been carried out, it appears that in newswire texts nominalised forms are less likely to appear in the first reference to an event, and more likely to appear in subsequent references.</Paragraph>
    <Paragraph position="1"> solely restricted to, carrying out the tasks specified in MUC-6: named entity recognition, coreference resolution, template element filling, and scenario template filling tasks (see DARPA (1995) for further details of the task descriptions). In addition, the system can generate a brief natural language summary of any scenario it has detected in a text. All these tasks are carried out by building a single rich discourse model of the text from which the various results are read off. The system is a pipelined architecture which processes a text one sentence at a time and consists of three principal processing stages: lexical preprocessing, parsing plus semantic interpretation, and discourse interpretation. The overall contributions of these stages may be briefly described as follows (see Gaizauskas et al. (1995) for further details): lexical preprocessing reads and tokenises the raw input text, tags the tokens with parts-ofspeech, performs morphological analysis, performs phrasal matching against lists of proper names; parsing and semantic interpretation builds lexical and phrasal chart edges in a feature-based formalism then does two pass chart parsing, pass one with a special named entity grammar, pass two with a general grammar, and, after selecting a 'best parse', constructs a predicate-argument representation of the current sentence; discourse interpretation adds the information from the predicate-argument representation to a hierarchically structured semantic net which encodes the system's world model, adds additional information presupposed by the input, performs coreference resolution between new and existing instances in the world model, and adds any information consequent upon the new input.</Paragraph>
    <Section position="1" start_page="75" end_page="76" type="sub_section">
      <SectionTitle>
2.1 MUC-6 Coreference Performance
</SectionTitle>
      <Paragraph position="0"> MUC-6 included a quantitatively evaluated coreference task, which required participating systems to propose coreference annotations for a set of texts.</Paragraph>
      <Paragraph position="1"> These annotations were then automatically scored against manually produced annotations for the same texts. The performance of the LaSIE system in this coreference task was 51% recall and 71% precision.</Paragraph>
      <Paragraph position="2"> This compares favourably with the highest scoring MUC-6 systems: the highest recall system scored 63% recall and 63% precision; the highest precision system scored 59% recall and 72% precision. Recall  here is a measure of how many correct (i.e. manually annotated) coreferences the system actually found, and precision is a measure of how many coreferences the system proposed were actually correct. For example, suppose there are 100 real coreference relations in a corpus and a system proposes 75, of which 50 are correct. Then its recall is 50/100 or 50% and its precision is 50/75 or 66.7%.</Paragraph>
      <Paragraph position="3"> The MUC-6 definition of the coreference task included several forms of NP coreference, not only pronominal relations. However, it did not include event coreference, which can be measured only indirectly via the information extraction task results, a topic to which we return in Section 6.</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="76" end_page="76" type="metho">
    <SectionTitle>
3 Discourse Interpretation
</SectionTitle>
    <Paragraph position="0"> The LaSIE system's 'world' or domain of interest is modelled by an inheritance-based semantic graph, using the XI knowledge representation language (Gaizauskas, 1995). In the graph classes of objects, events, and attributes appear as nodes; each node may have associated with it an attribute-value structure and these structures are inherited down the graph. The higher levels of the graph, or ontology, for the management succession task have the structure shown in Figure 1. Two simple attribute-value structures are also shown in the graph, connected by dashed lines to the nodes with which they are associated.</Paragraph>
    <Paragraph position="1"> Attribute-value structures are just sets of attribute:value pairs where the value for an attribute may either be static, as in the pair animate:yes, which is associated with the person node, or dynamic, where the value is dependent on various conditions, the evaluation of which makes reference to other information in the model. Certain special attribute types, presupposition and consequence, may also return values which are used at specific points to modify the current state of the model.</Paragraph>
    <Paragraph position="2"> As a discourse is processed, discourse entities (objects and events introduced by the text) are added as new nodes in the graph beneath their parent class and have associated with them an attribute-value structure containing both inherited and discoursesupplied attributes. This process may involve hypothesising new implicit entities if they are not available explicitly in the text, or have not been discovered by the parser, but are required role players for a given event type. Knowledge about required roles is represented via attributes in the world model. For example, in Figure 1 we see that a retire event requires a logical subject of type person and an entity of this type will be hypothesised if it is not available from the text.</Paragraph>
  </Section>
  <Section position="5" start_page="76" end_page="78" type="metho">
    <SectionTitle>
4 Coreference Resolution
</SectionTitle>
    <Paragraph position="0"> After each sentence in a text is added to the 'world model', gradually forming a discourse-specific model, a coreference procedure is applied to attempt to resolve, or merge, each of the newly added instances with instances currently in the discourse model. Coreference resolution is performed by comparing instances from several candidate sets, each of which is a set of pairs of instances where one element is an instance from the current input sentence and the other an instance occurring earlier in the text, which may be coreferential. The algorithm proceeds as follows for each instance pair being considered: 1. Ensure semantic type consistency To determine semantic consistency requires establishing a path in the semantic graph between the semantic types of the two instances. If a path can be found a semantic similarity score is calculated using the inverse of the length of the path (measured in nodes) between the two types.</Paragraph>
    <Paragraph position="1"> For event instances, a path is valid if both event types are dominated by a task-specific top node, i.e. both types must be potential sub-events of an event required by the current IE template.</Paragraph>
    <Paragraph position="2"> For example, 'hire' and 'retire' are both sub-events of the 'succession' event in the ontology sketched above.</Paragraph>
    <Paragraph position="3"> For instances of the object class, a path is valid if the two types stand in a dominance relation, i.e. the types are ordered in the ontology. For example, 'company' is a sub-class of 'organisation' so these type are ordered (and have a semantic similarity score of 0.5).</Paragraph>
    <Paragraph position="4"> If no valid path can be found the attempt to resolve the two instances is abandoned.</Paragraph>
    <Paragraph position="5"> . Ensure attribute consistency Certain attributes, e.g. animate and time, are specified in the ontology as taking a single fixed value for any particular instance. If two instances being compared have a common attribute of this type, the values must be identical or the attempted resolution is abandoned.</Paragraph>
    <Paragraph position="6"> Type specific coreference constraints are then examined by attempting to inherit a distinct attribute. If this attribute can be derived from any of the instances' superclasses the attempted resolution of the current pair is abandoned.</Paragraph>
    <Paragraph position="7">  Constraints on the various event types are detailed in the following section.</Paragraph>
    <Paragraph position="8"> . Calculate a similarity score The semantic similarity score is summed with an attribute similarity score to give an overall score for the current pair of instances. The attribute similarity score is established by finding the ratio of the number of shared multi-valued attributes with compatible values, against the total number of the instances' attributes.</Paragraph>
    <Paragraph position="9"> After each pair m a candidate set has either been assigned a similarity score or has been rejected on grounds of inconsistency, the highest scoring pair (if any score at all) are merged in the discourse model. If several pairs have equal similarity scores then the pair with the closest realisations in the text will be merged. The merging of instances involves the removal of the least specific instance (i.e. the highest in the ontology) and the addition of all its attributes to the other instance.</Paragraph>
    <Section position="1" start_page="77" end_page="78" type="sub_section">
      <SectionTitle>
4.1 Event Coreference
</SectionTitle>
      <Paragraph position="0"> The constraints on events as used in Step 2 of the general coreference algorithm above can be associated with any event node in the ontology, and will then be inherited by all instances of all sub-event types. The constraints currently used can be categorised in the following way: 1. General task-independent constraints are associated with the top-level event node. For example two event instances are defined as distinct (i.e. not coreferential) if they have incompatible times. At present this simply means that two events with different tenses cannot be resolved, but clearly a more detailed model of event times is required, particularly as Crowe (1996) shows how temporal phrases are consistently useful in distinguishing and recognising events 3.</Paragraph>
      <Paragraph position="1">  2. General task-specific constraints are, for the management succession task, associated with the succession_event node. For example, the constraint that two instances must be distinct if they involve different organisations or different management positions.</Paragraph>
      <Paragraph position="2"> 3. More specific constraints are represented at  lower and possibly verb-specific nodes. For example, an incoming_event (e.g. hire, promote) is distinct from a changeover_event (e.g. replace, succeed) if the former's logical object is distinct from the latter's logical subject.</Paragraph>
      <Paragraph position="3"> The determination of distinct or compatible event roles requires the application of the coreference mechanism to instances of the object class (the role players in the event). The same algorithm is used but the inherited constraints will be those associated with the object nodes in the ontology. For ex3It is possible to represent a time scale within the current XI formalism and then associate each input event with a point on the scale. Each point can be treated as a potential interval and be expanded to include the times of sub-events. The representation and use of this more detailed model is currently under investigation.</Paragraph>
      <Paragraph position="4">  ample, indefinite noun phrases cannot be anaphors, pronouns should be resolved within the current paragraph, definite noun phrases within the last two paragraphs, etc. Full details and an evaluation of the coreference constraints on object instances can be found in Gaizauskas and Humphreys (1997a).</Paragraph>
      <Paragraph position="5"> The constraints above are similar to those used in the FASTUS IE system (Appelt et al., 1995) and by Sown (1984), where the merging takes place between template structures, considering special conditions for the unification of variables in template slots. However, the general approach here has more in common with Whittemore and Macpherson (1991) or Zarri (1992), where event merging is carried out within the underlying knowledge representation.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="78" end_page="79" type="metho">
    <SectionTitle>
5 A Worked Example
</SectionTitle>
    <Paragraph position="0"> This section describes the operation of the general coreference mechanism for the example (3) presented in the introduction, concentrating on the effect of the various constraints on event instances. We reproduce the two sentences in (3) here: (3a) The sell-off followed the resignation late Monday of Freddie Heller, the president of Renard Broadcasting Co.</Paragraph>
    <Paragraph position="1"> (3b) Yesterday, Renard named Susan B. Kempham, chairman of Renard Inc. % television production arm, to succeed him to succeed him.</Paragraph>
    <Paragraph position="2"> The full semantic representation of these sentences as produced by the parser/semantic interpreter for input to the discourse interpreter is:</Paragraph>
    <Paragraph position="4"> The nominalisation of the verb resign in (3a) leads to the presupposition of an outgoing_even% which in turn leads to hypothesised objects for a related person, post and organisation (these presuppositions are stored as attributes of the outgoing_event in the world model). The coreference mechanism will then be applied to these objects and, in this case, will be able to resolve all three within the same sentence. The resign event therefore forms a complete succession event for the management succession IE task.</Paragraph>
    <Paragraph position="5"> Both verbs in (3b), the incoming_event name and the changeover_event succeed, will cause the introduction of succession event instances into the discourse model, each of which will cause the hypothesis of a related person, post and organisation. Attributes of the name event will add additional constraints to its hypothesised objects, including the specification that the organisation should be a potential subject of the verb, the person a potential logical object, and the post a potential complement.</Paragraph>
    <Paragraph position="6"> Objects with the required features will be found by the coreference mechanism for the organisation and person, but not the post. The succeed event will also cause the hypothesis of an additional person, with the constraints that one must be incoming, and a potential logical subject of the verb, and the other outgoing, and a potential logical object. The succeed event's hypothesised organisation and post will be resolved with the same objects as the resign event from the previous sentence.</Paragraph>
    <Paragraph position="7"> The general constraints on coreferential succession events are therefore satisfied for the succeed and resign events, and the restrictions on the more specific subclasses must then be considered. The relevant restriction here is that a changeover_event must share its logical object with the logical subject of an outgoing_event. This will require the application of the coreference mechanism for objects to resolve the pronoun him. A correct resolution with Freddie Heller will then allow the two events to be resolved.</Paragraph>
    <Paragraph position="8"> The succeed and name events will also be resolved similarly, using the restriction that a changeover_event must share its logical subject  with the logical object of an incoming_event. In this case the infinitive form of the succeed verb will have no explicit logical subject, but one will be hypothesised and resolved with the best antecedent of the required type (person), here Susan B. Kempham.</Paragraph>
    <Paragraph position="9"> The two events can therefore be merged, to result in the representation of a single succession event with Freddie Heller outgoing and Susan B. Kempham incoming. null</Paragraph>
  </Section>
class="xml-element"></Paper>