<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1031">
  <Title>A Flexible POS Tagger Using an Automatically Acquired Language Model*</Title>
  <Section position="10" start_page="243" end_page="243" type="ackno">
    <SectionTitle>
8 Further Work
</SectionTitle>
    <Paragraph position="0"> Further work is still to be done in the following directions: null * Perform a thorough analysis of the noise in the WSJ corpus to determine a realistic upper * bound for the performance that can be expected from a POS tagger.</Paragraph>
    <Paragraph position="1"> On the constraint learning algorithm: * Consider more complex context features, such as non-limited distance or barrier rules in the style of (Samuelsson et al., 1996).</Paragraph>
    <Paragraph position="2"> * Take into account morphological, semantic and other kinds of information.</Paragraph>
    <Paragraph position="3"> * Perform a global smoothing to deal with low-frequency ambiguity classes.</Paragraph>
    <Paragraph position="4"> On the tagging algorithms * Study the convergence properties of the algorithm to decide whether the lower results at convergence are produced by the noise in the corpus.</Paragraph>
    <Paragraph position="5"> * Use back-off techniques to minimize interferences between statistical and learned constraints. null * Use the algorithm to perform simultaneously POS tagging and word sense disambiguation, to take advantage of cross influences between both kinds of information.</Paragraph>
  </Section>
class="xml-element"></Paper>