<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-1023">
  <Title>STOCK OF SHARED KNOWLEDGE - - A TOOL FOR SOLVING PRONOMINAL ANAPHORA</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 .INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> In our paper at Coling'90 we followed up the investigations presented in HajEov~i, Vrbov~ (1982) and proposed an algorithm for solving pronominal anaphora with the use of &amp;quot;stock of shared knowledge&amp;quot; (SSK) - an abstract representation of the hierarchy of salience of the items of the knowledge assumed by the speaker to be shared by him and the hearer. The changes of degrees of salience were dependent solely on the bipolar division of the sentence into its topic and focus parts, respectively. In particular, the rules for computing the degrees of salience were specified as follows: (i) the items referred to in the focus part of the utterance be it by a noun or by a stressed pronoun receive the highest degree of salience (MAX); (ii) the items referred to by a noun in the topic part of the sentence are activated one degree less (i) to replace the binary account of topic/focus articulation of the sentence by a more atomic distinction between the contextually bound and non-bound elements of the sentence, thus enriching the numerical system of possible degrees of salience; (ii) to account explicitly for the empirical observations that items mentioned throughout the discourse are more likely to be referred to than those mentioned only once.</Paragraph>
    <Paragraph position="1"> In this paper we would like to argue that other important features should he taken into account in building the new evaluation system for the SSK. We believe that for a more sophisticated treatment of pronominal anaphora, an account of SSK must also allow for: (iii) a reflection of the topology of the surface structure of the text, in the simpliest form in terms of the distance of the possible antecedent and a ACRES DE COLING-92, NANTES, 23-28 Aofrr 1992 1 2 7 Pgoc. OF COLING-92, NANTES, AUO. 23-28, 1992 refering expression measured by the number of interfering objects between them with respect to the sentence and paragraph boundaries; (iv) a capturing of some associations between lexieal units describing objects in the text. We have limited our attention only to syntactic associations between governing and dependent words in the syntactic structure of the sentence. More general treatment of associations requires the use of semantic and/or pragmatic information (eg.</Paragraph>
    <Paragraph position="2"> semantic features, knowledge base etc.) which is not taken into consideration in the present version of the algorithm, but forms a promising subject of further investigations of possible improvements of the algorithm.</Paragraph>
    <Paragraph position="3"> Taking these observations into account, we present a new, enriched model of SSK here. In Section 2 we briefly discuss the relevance of the above mentioned features for anapbora resolution.</Paragraph>
    <Paragraph position="4"> Section 3 gives a proposal of the organization of SSK, together with the rules evaluating changes in degrees of salience of its items and a general algorithm for reference assignment based on the use of SSK. The possibility of customizing the algorithm for the purposes of a special language under consideration (in our case Czech) is discussed in Section 4.</Paragraph>
  </Section>
class="xml-element"></Paper>