<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1029">
  <Title>A Class-based Probabilistic approach to Structural Disambiguation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Knowledge of which words are able to fill particular a.rgument slots of a. l?redlca.te ca,n be used tbr structural disa.mbiguation. In the following example (Charnial~, 1993), the fact that dog, rather than prize, is often the su.1)ject of r'lm, can t)e used to decide on the attachment site of the relative clause: Fred awarded a prize for the dog that ran the fastest We describe a proposal for acquiring such knowledge, and as in other recent work in this area (Resnik, 1993; l,i and Abe, t998), a probabilistic approach is taken. Using probabilities accords with the intuition that there are no absolute constraints on the arguments of predicates, bu.t rather that constraints are satisfied to a certain degree (Resnik, 1993). Unfortunately, defining probabilities in terms of words leads to a model with a vast number of parameters, resulting in a sparse data problem. To overcome this, we propose to define a probability model in terms of senses from a semantic hierarchy, exploiting the fact that senses of nouns can be grouped together into semantically similar classes.</Paragraph>
    <Paragraph position="1"> We use the semantic hierarchy of noun senses in WordNet (Fellbamn, 1.998), which consists of qexicalised concepts' related by the qs-a-kindof' relation. If c' is a kind of c, then c is a hypcrnym of c', and c' a hyponym of c. Counts are passed u.p the hierarchy fl'om the senses of nouns appearing in the data. Thus if cat chicl~cn a.ppears in the data, th.e count for this item passes u\]) to (meat}, (good}, and all the other hypernyms of that sense of chicken. 1 In. order to estimate the probability that a sense of chichcn ~tppea.rs as the object of the verb cat, we represent (chicken} using a. suitable hypern3qn , such as (:eood), and base our probability estimate on that instead. The level at which (chicken) is represented is cruciah it should be high enough for adequate counts to have accumulated, but not too high so that the hypernym is no longer representative of (chicken}. An exanlple of a hypernym whidl would be too high is (erttity), as not all entities are semantically similar with respect to the object position ot7 cat.</Paragraph>
    <Paragraph position="2"> The problem of choosing an appropria.te level in the h.ierarchy at which to represent a particular noun sense (given a predicate and argument position) has been investigated by Resnik (1993), Li and Abe (1998) and ll,iba,s (1995).</Paragraph>
    <Paragraph position="3"> The learning mechanism presented \]lore is a novel approach based on tinding semantically similar sets of concepts in a hierarchy. We demonstrate the effectiveness of our approach using a PP-attachment experiment.</Paragraph>
  </Section>
class="xml-element"></Paper>