<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1007">
  <Title>Frame Semantic Enhancement of Lexical-Semantic Resources</Title>
  <Section position="2" start_page="0" end_page="57" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The intuition that semantic analysis can make a positive contribution to language-based applications has motivated the development of a number of lexical-semantic resources. Prominent among them are WordNet,1 PropBank,2 and FrameNet.3 The potential contribution of these resources is constrained by the information they contain and the level of effort involved in their development.</Paragraph>
    <Paragraph position="1"> For example, semantic annotation tasks (Baker et al., 2004) typically assign semantic roles to the arguments of predicates. The benefit of the semantic annotation is constrained by the presence and quality of semantic roles in the lexical-semantic resource(s) used. Gildea and Jurafsky (2002) suggest that the availability of semantic annotation of this sort is useful for information extraction, word sense disambiguation, machine translation, text summarization, text mining, and speech recognition.</Paragraph>
    <Paragraph position="2">  Other tasks rely on the identification of semantic relationships to recognize lexical chains (sets of semantically related words that enable a text to be cohesive) (Morris and Hirst, 1991). The success of this work is constrained by the set of semantic relationship types and instantiations underlying the recognition of lexical chains. As Stokes's dissertation (2004) notes, lexical cohesion has been used in discourse analysis, text segmentation, word sense disambiguation, text summarization, topic detection and tracking, and question answering.</Paragraph>
    <Paragraph position="3"> Unfortunately, most lexical-semantic resources, including those previously mentioned, are the product of considerable ongoing human effort. Given the high development costs associated with these resources, the possibility of enhancing them on the basis of complementary resources that are produced automatically is welcome.</Paragraph>
    <Paragraph position="4"> This paper demonstrates several of the characteristics and benefits of SemFrame (Green et al., 2004; Green and Dorr, 2004), a system that produces such a resource.</Paragraph>
    <Paragraph position="5">  cause of the labor-intensive nature of its development, is incomplete. The identification of new frames thus helps fill in gaps in FrameNet.</Paragraph>
    <Paragraph position="6"> 4. In addition to complementing FrameNet, SemFrame could be used as a more systematic source of semantic roles for PropBank or could serve as the basis for adding frame semantic relationships to WordNet.</Paragraph>
    <Paragraph position="7"> The rest of the paper is organized as follows: Section 2 discusses lexical-semantic resources that could be enhanced by using SemFrame's output.</Paragraph>
    <Paragraph position="8"> Section 3 sets out how SemFrame works, with Sub-sections 3.1 and 3.2 explaining, respectively, the identification of lexical units that evoke shared semantic frames and the generation of the internal structure of those frames. Section 4 discusses how we evaluate SemFrame's output. Finally, Section 5 summarizes SemFrame's contributions and sketches future directions in its development.</Paragraph>
  </Section>
class="xml-element"></Paper>