<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1005">
  <Title>Automatically Distinguishing Literal and Figurative Usages of Highly Polysemous Verbs</Title>
  <Section position="8" start_page="44" end_page="45" type="concl">
    <SectionTitle>
7 Discussion and Concluding Remarks
</SectionTitle>
    <Paragraph position="0"> Recently, there has been increasing awareness of the need for appropriate handling of multiword expressions (MWEs) in NLP tasks (Sag et al., 2002). Some research has concentrated on the automatic acquisition of semantic knowledge about certain classes of MWEs, such as compound nouns or verb particle constructions (VPCs) (e.g., Lin, 1999; McCarthy et al., 2003; Villavicencio, 2003). Previous research on LVCs, on the other hand, has primarily focused on their automatic extraction (e.g., Grefenstette and Teufel 1995; Dras and Johnson 1996; Moir'on 2004; though see Stevenson et al. 2004).</Paragraph>
    <Paragraph position="1"> Like most previous studies that focus on semantic properties of MWEs, we are interested in the issue of compositionality. Our COMP measure aims to identify a continuum along which a light verb contributes to the semantics of an expression. In this way, our work combines aspects of earlier work on VPC semantics. McCarthy et al. (2003) determine a continuum of compositionality of VPCs, but do not distinguish the contribution of the individual components. Bannard et al. (2003), on the other hand, look at the separate contribution of the verb and particle, but assume that a binary decision on the compositionality of each is sufficient.</Paragraph>
    <Paragraph position="2"> Previous studies determine compositionality by looking at the degree of distributional similarity between an expression and its component words (e.g., McCarthy et al., 2003; Bannard et al., 2003; Baldwin et al., 2003). Because light verbs are highly polysemous and frequently used in LVCs, such an approach is not appropriate for determining their contribution to the semantics of an expression. We instead examine the degree to which a light verb usage is &amp;quot;similar&amp;quot; to the prototypical LVC, through a statistical comparison of its behaviour within different syntactic patterns. Syntactic flexibility and semantic compositionality are known to be strongly correlated for many types of MWEs (Nunberg et al., 1994). We thus intend to extend our approach to include other polysemous verbs with metaphorical extensions.</Paragraph>
    <Paragraph position="3"> Our compositionality measure correlates well with the literal/figurative spectrum represented in  human judgments. We also aim to determine finer-grained distinctions among the identified figurative usages of a light verb, which appear to relate to the semantic class of its complement. Semantic class knowledge may enable us to elucidate the types of relations between a light verb and its complement such as those determined in the work of Wanner (2004), but without the need for the manually labelled training data which his approach requires.</Paragraph>
    <Paragraph position="4"> Villavicencio (2003) used class-based knowledge to extend a VPC lexicon, but assumed that an unobserved VPC is not acceptable. We instead believe that more robust application of class-based knowledge can be achieved with a better estimate of the acceptability of various expressions.</Paragraph>
    <Paragraph position="5"> Work indicating acceptability of MWEs is largely limited to collocational analysis using PMI-based measures (Lin, 1999; Stevenson et al., 2004). We instead use a probability formula that enables flexible integration of LVC-specific linguistic properties. Our ACPT measure yields good correlations with human acceptability judgments; indeed, the average increase over the baseline is about twice as high as that of the acceptability measure proposed by Stevenson et al. (2004). Although ACPT also somewhat reflects different patterns across semantic classes, the results clearly indicate the need for incorporating more knowledge into the measure to capture class-based behaviour more consistently.</Paragraph>
    <Paragraph position="6"> The work presented here is preliminary, but is the first we are aware of to tie together the two issues of compositionality and acceptability, and relate them to the notion of class-based meaning extensions of highly polysemous verbs. Our on-going work is focusing on the role of the noun component of LVCs, to determine the compositional contribution of the noun to the semantics of the expression, and the role of noun classes in influencing the meaning extensions of light verbs.</Paragraph>
  </Section>
class="xml-element"></Paper>