<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1065">
  <Title>Automatic Labeling of Semantic Roles</Title>
  <Section position="4" start_page="0" end_page="0" type="relat">
    <SectionTitle>
3 Related Work
</SectionTitle>
    <Paragraph position="0"> Assignment of semantic roles is an important part of language understanding, and has been attacked by many computational systems. Traditional parsing and understanding systems, including implementations of uni#0Ccation-based grammars such as HPSG #28Pollard and Sag, 1994#29, rely on handdeveloped grammars which must anticipate eachway in which semantic roles may be realized syntactically. Writing such grammars is time-consuming, and typically such systems have limited coverage.</Paragraph>
    <Paragraph position="1"> Data-driven techniques have recently been applied to template-based semantic interpretation in limited domains by #5Cshallow&amp;quot; systems that avoid complex feature structures, and often perform only shallow syntactic analysis. For example, in the context of the Air Traveler Information System #28ATIS#29 for spoken dialogue, Miller et al. #281996#29 computed the probability that a constituent such as #5CAtlanta&amp;quot; #0Clled a semantic slot such as Destination in a semantic frame for air travel. In a data-driven approach to information extraction, Rilo#0B #281993#29 builds a dictionary of patterns for #0Clling slots in a speci#0Cc domain such as terrorist attacks, and Rilo#0B and Schmelzenbach #281998#29 extend this technique to automatically derive entire case frames for words in the domain. These last systems make use of a limited amount of hand labor to accept or reject automatically generated hypotheses. They show promise for a more sophisticated approach to generalize beyond the relatively small number of frames considered in the tasks. More recently, a domain independent system has been trained on general function tags such as Manner and Temporal by Blaheta and Charniak #282000#29.</Paragraph>
  </Section>
class="xml-element"></Paper>