<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1055">
  <Title>Using Machine Learning to Maintain Rule-based Named-Entity Recognition and Classification Systems Georgios Petasis +, Frantz Vichot SS, Francis Wolinski SS</Title>
  <Section position="9" start_page="2" end_page="2" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have proposed an alternative use of machine learning in named-entity recognition and classification. Instead of constructing an autonomous NERC system, the system constructed with the use of machine learning assists in the maintenance of a rule-based NERC system. An important feature of the approach is the use of a supervised learning method, without the need for manual tagging of training data. The proposed approach was evaluated with success for two different languages: Greek and French.</Paragraph>
    <Paragraph position="1"> On-going work aims at reducing the number of disagreements between the two systems down to those that are essential for the improvement of the system. Currently, there are many cases where the two systems disagree, but the rule-based system is correct.</Paragraph>
    <Paragraph position="2"> Another extension that we are examining is to train a NERC system to not only classify, but also recognise NEs. We believe that this extension will lead to the identification of more problematic cases in the recognition phase.</Paragraph>
    <Paragraph position="3"> In conclusion, the method presented in this paper proposes a simple and effective use of machine learning for the maintenance of rule-based systems. The scope of this approach is clearly wider than that examined here, i.e., named-entity recognition.</Paragraph>
  </Section>
class="xml-element"></Paper>