<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1207">
  <Title>Classifying Particle Semantics in English Verb-Particle Constructions</Title>
  <Section position="3" start_page="0" end_page="45" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A challenge in learning the semantics of multiword expressions (MWEs) is their varying degrees of compositionality--the contribution of each component word to the overall semantics of the expression. MWEs fall on a range from fully compositional (i.e., each component contributes its meaning, as in frying pan) to non-compositional or idiomatic (as in hit the roof ). Because of this variation, researchers have explored automatic methods for learning whether, or the degree to which, an MWE is compositional (e.g., Lin, 1999; Bannard et al., 2003; McCarthy et al., 2003; Fazly et al., 2005).</Paragraph>
    <Paragraph position="1"> However, such work leaves unaddressed the basic issue of which of the possible meanings of a component word is contributed when the MWE is (at least partly) compositional. Words are notoriously ambiguous, so that even if it can be determined that an MWE is compositional, its meaning is still unknown, since the actual semantic contribution of the components is yet to be determined. We address this problem in the domain of verb-particle constructions (VPCs) in English, a rich source of MWEs.</Paragraph>
    <Paragraph position="2"> VPCs combine a verb with any of a finite set of particles, as in jump up, figure out, or give in. Particles such as up, out, or in, with their literal meaning based in physical spatial relations, show a variety of metaphorical and aspectual meaning extensions, as exemplified here for the particle up:  (1a) The sun just came up. [vertical spatial movement] (1b) She walked up to him. [movement toward a goal] (1c) Drink up your juice! [completion] (1d) He curled up into a ball. [reflexive movement]  Cognitive linguistic analysis, as in Lindner (1981), can provide the basis for elaborating this type of semantic variation.</Paragraph>
    <Paragraph position="3"> Given such a sense inventory for a particle, our goal is to automatically determine its meaning when used with a given verb in a VPC. We classify VPCs according to their particle sense, using statistical features that capture the semantic and syntactic properties of verbs and particles. We contrast these with simple word co-occurrence features, which are often used to indicate the semantics of a target word. In our experiments, we focus on VPCs using the particle up because it is highly frequent and has a wide range of meanings.</Paragraph>
    <Paragraph position="4"> However, it is worth emphasizing that our feature space draws on general properties of VPCs, and is not specific to this particle.</Paragraph>
    <Paragraph position="5"> A VPC may be ambiguous, with its particle occurring in more than one sense; in contrast to (1a), come up may use up in a goal-oriented sense as in  The deadline is coming up. While our long-term goal is token classification (disambiguation) of a VPC in context, following other work on VPCs (e.g., Bannard et al., 2003; McCarthy et al., 2003), we begin here with the task of type classification. Given our use of features which capture the statistical behaviour relevant to a VPC across a corpus, we assume that the outcome of type classification yields the predominant sense of the particle in the VPC. Predominant sense identification is a useful component of sense disambiguation of word tokens (McCarthy et al., 2004), and we presume our VPC type classification work will form the basis for later token disambiguation.</Paragraph>
    <Paragraph position="6"> Section 2 continues the paper with a discussion of the features we developed for particle sense classification. Section 3 first presents some brief cognitive linguistic background, followed by the sense classes of up used in our experiments. Sections 4 and 5 discuss our experimental set-up and results, Section 6 related work, and Section 7 our conclusions.</Paragraph>
  </Section>
class="xml-element"></Paper>