<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1017">
  <Title>Constructing Semantic Space Models from Parsed Corpora</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Discussion
</SectionTitle>
    <Paragraph position="0"> In this paper we presented a novel semantic space model that enriches traditional vector-based models with syntactic information. The model is highly general and can be optimised for different tasks. It extends prior work on syntax-based models (Grefenstette, 1994; Lin, 1998), by providing a general framework for defining context so that a large number of syntactic relations can be used in the construction of the semantic space.</Paragraph>
    <Paragraph position="1"> Our approach differs from Lin (1998) in three important ways: (a) by introducing dependency paths we can capture non-immediate relationships between words (i.e., between subjects and objects), whereas Lin considers only local context (dependency edges in our terminology); the semantic space is therefore constructed solely from isolated head/modifier pairs and their inter-dependencies are not taken into account; (b) Lin creates the semantic space from the set of dependency edges that are relevant for a given word; by introducing dependency labels and the path value function we can selectively weight the importance of different labels (e.g., subject, object, modifier) and parametrize the space accordingly for different tasks; (c) considerable flexibility is allowed in our formulation for selecting the dimensions of the semantic space; the latter can be words (see the leaves in Figure 1), parts of speech or dependency edges; in Lin's approach, it is only dependency edges (features in his terminology) that form the dimensions of the semantic space.</Paragraph>
    <Paragraph position="2"> Experiment 1 revealed that the dependency-based model adequately simulates semantic priming. Experiment 2 showed that a model that relies on rich context specifications can reliably distinguish between different types of lexical relations. Our results indicate that a number of NLP tasks could potentially benefit from dependency-based models.</Paragraph>
    <Paragraph position="3"> These are particularly relevant for word sense discrimination, automatic thesaurus construction, automatic clustering and in general similarity-based approaches to NLP.</Paragraph>
  </Section>
class="xml-element"></Paper>