<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1105">
  <Title>Semantic Tagging using a Probabilistic Context Free Grammar *</Title>
  <Section position="3" start_page="38" end_page="39" type="intro">
    <SectionTitle>
RESTOR INDUSTRIES Inc. (Orlando, Fla.) --
</SectionTitle>
    <Paragraph position="0"> Hensley E. West, 50 years old, was named president of this telecommunications-product concern. Mr. West, who most recently was a group vice president for DSC Communications Corp. in Dallas, fills a vacancy created by the retirement last September of John Bradley, 63.</Paragraph>
    <Paragraph position="1">  the text.</Paragraph>
    <Paragraph position="2"> Most systems described in the MUC-6 proceedings followed the following three stages of processing in mapping an input text to a set of output templates: I We've just shown the most important, &amp;quot;core&amp;quot; slots for tie task the MUC-6 specification includes additional information such as the reason for the change, the title of the people involved etc.  1) Pattern matching at the sentence level. This is the task that is approached in this paper. In the text in figure 1, &amp;quot;Hensley E. West, 50 years old, was named president of this telecommunications-product concern&amp;quot; would be processed to give { IN = &amp;quot;Hensley E. West&amp;quot;, POST = &amp;quot;'president&amp;quot;, COMPANY = &amp;quot;this telecommunications-product concern&amp;quot;, VERB = &amp;quot;named&amp;quot; } and &amp;quot;.... the re- null tirement last September of John Bradley .... &amp;quot; would give { OUT = &amp;quot;John Bradley&amp;quot;, NOUN = &amp;quot;retirement&amp;quot;, IND = &amp;quot;resignation&amp;quot;} 2) Coreference. Pronouns and definite NPs arc resolved to their antecedents. For example, &amp;quot;this telecommunications-product concern&amp;quot; would be resolved to &amp;quot;RESTOR INDUSTRIES Inc.&amp;quot;. This stage is important because pronouns and definite noun-phrases like &amp;quot;this telecommunications-product concern&amp;quot; are not informative slot-fillers.</Paragraph>
    <Paragraph position="3"> 3) Merging. The information in a template may be  spread across several sentences. In the merging stage the information from multiple mentions of the same event is merged into a single template. In the example, the information centered around &amp;quot;named&amp;quot; and &amp;quot;retirement&amp;quot; would be identified as referring to the same event, and would be combined to give { IN = &amp;quot;Hensley E. West&amp;quot;, OUT = &amp;quot;John Bradley&amp;quot;, POST = &amp;quot;president&amp;quot;, COMPANY =</Paragraph>
  </Section>
class="xml-element"></Paper>