<?xml version="1.0" standalone="yes"?>
<Paper uid="M91-1022">
  <Title>Assuming C-BOMBING-TEMPLATE and C-INJURY-TEMPLATE have same R-INSTRUMENT Assuming C-BOMBING-TEMPLATE and C-DAMAGE-TEMPLATE have same R-INSTRUMENT Assuming C-BOMBING-TEMPLATE and C-INJURY-TEMPLATE have same R-DATE Assuming C-BOMBING-TEMPLATE and C-DAMAGE-TEMPLATE have same R-DATE Assuming C-BOMBING-TEMPLATE and C-INJURY-TEMPLATE have same R-PERPETRATOR Assuming C-BOMBING-TEMPLATE and C-DAMAGE-TEMPLATE have same R-PERPETRATOR Assuming C-BOMBING-TEMPLATE and C-INJURY-TEMPLATE have same R-TARGET Assuming C-BOMBING-TEMPLATE and C-DAMAGE-TEMPLATE have same R-TARGET Comparison of Program Answers with Answer Key The NLTooLsET results for TST1-0099 were the following templates :</Title>
  <Section position="7" start_page="147" end_page="147" type="concl">
    <SectionTitle>
SUMMARY AND CONCLUSIO N
</SectionTitle>
    <Paragraph position="0"> MUC-3 is a very difficult task, involving a combination of language interpretation, conceptual and domain knowledge, along with many rules and strategies fo l. template filling . The examples given here show not onl y how our system performs this, but hopefully some of the limitations of the system and the penalties paid i n the scoring for these mistakes . While it is very difficult to attribute effects in the score to particular functions of the programs, there is no question that the task adequately exercises most of the current features of our system . It is equally clear that there is ample room for improvements from promising research areas, such as implicit event reference, discourse processing and representation, and general reference, as well as from task-specific processing and more well-known problems such as general inference .</Paragraph>
  </Section>
class="xml-element"></Paper>