<?xml version="1.0" standalone="yes"?>
<Paper uid="M95-1006">
  <Title>Regarding ST</Title>
  <Section position="3" start_page="0" end_page="55" type="intro">
    <SectionTitle>
SUMMARY OF WHAT'S NE W
</SectionTitle>
    <Paragraph position="0"> In the last two years we have ported part or all of the PLUM system to several new languages (Chinese, German , Japanese, and Spanish) and new domains (law enforcement, name finding, heterogeneous newswire sources, and labo r negotiations) . Though we have a new, fully trainable, full parser of English (Magerman, 1995), there wa s insufficient time to integrate it into PLUM for the evaluation ; as an independent component, it appears to hav e achieved the highest published evaluation scores for parsers .</Paragraph>
    <Paragraph position="1"> The new software developments employed in MUC-6 are  We have begun making a distinction between lightweight techniques and heavyweight processing. IdentiFinder i s made up solely of lightweight techniques, i .e., those that rely only on local processing, do not involve dee p understanding, and can be optimized. The lightweight procedures in IdentiFinder are SGML recognition, hidde n Markov models, finite state pattern recognition, and SGML output .</Paragraph>
    <Paragraph position="2"> By heavyweight processing, we mean procedures that depend on global evidence and involve deeper understanding . The SPATTER full parser of English and the new semantic inference procedure are examples .</Paragraph>
  </Section>
class="xml-element"></Paper>