<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1029">
  <Title>Nymble: a High-Performance Learning Name-finder</Title>
  <Section position="12" start_page="199" end_page="199" type="concl">
    <SectionTitle>
6. Conclusions
</SectionTitle>
    <Paragraph position="0"> We have shown that using a fairly simple probabilistic model, finding names and other numerical entities as specified by the MUC tasks can be performed with &amp;quot;near-human performance&amp;quot;, often likened to an F of 90 or above. We have also shown that such a system can be gained efficiently and that, given appropriately and consistently marked answer keys, it can be trained on languages foreign to the trainer of the system; for example, we do not speak Spanish, but trained Nymble on answer keys marked by native speakers. None of the formalisms or techniques presented in this paper is new; rather, the approach to this task the model itself--is wherein lies the novelty. Given the incredibly difficult nature of many NLP tasks, this example of a learned, stochastic approach to name-finding lends credence to the argument that the NLP community ought to push these approaches, to find the limit of phenomena that may be captured by probabilistic, finite-state methods.</Paragraph>
  </Section>
class="xml-element"></Paper>