<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2236">
  <Title>Automatic Construction of Frame Representations for Spontaneous Speech in Unrestricted Domains</Title>
  <Section position="3" start_page="0" end_page="1448" type="intro">
    <SectionTitle>
2 Shallow Semantic Structures
</SectionTitle>
    <Paragraph position="0"> The two main representations we are building on are the following: * chunks: these correspond mostly to basic (i.e., non-attached) phrasal constituents * frames: these are built from the parsed chunks according to subcategorization constraints extracted from the WordNet lexicon The chunks are defined in a similar way as in (Abney, 1996), namely as &amp;quot;non-recursive phrasal units&amp;quot;; they roughly correspond to the standard linguistic notion of constituents, except that there are no attachments made (e.g., a PP to a NP) and that a verbal chunk does not include any of its arguments but just consists of the verbal complex (auxiliary/main verb), including possibly inserted adverbs and/or negation particles.</Paragraph>
    <Paragraph position="1"> All frames are being generated on the basis of &amp;quot;short clauses&amp;quot; which we define as minimal clausal units that contain at least one subject and an inflected verbal form) 2 To produce the list of all possible subcategorization frames, we first extracted all verbal tokens from the tagged SWITCHBOARD corpus and then retrieved the frames from WordNet. Table 1 provides a summary of this pre-calculation.</Paragraph>
    <Paragraph position="2">  separately. They will, however, have to be &amp;quot;linked&amp;quot; to the phrase they modify.</Paragraph>
    <Paragraph position="3"> 2We are also considering to take even shorter units as basis for the mapping that would, e.g., include non-inflected clausal complements. The most convenient solution has yet to be determined.</Paragraph>
  </Section>
class="xml-element"></Paper>