<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1062">
  <Title>Annealing Techniques for Unsupervised Statistical Language Learning</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have reviewed the DA algorithm, describing it as a generalization of EM with certain desirable properties, most notably the gradual increase of difficulty of learning and the ease of implementation for NLP models. We have shown how DA can be used to improve the accuracy of a tri-gram POS tagger learned from an unlabeled corpus. We described a potential shortcoming of DA for NLP applications--its failure to exploit good initializers--and then described a novel algorithm, skewed DA, that solves this problem. Finally, we reported significant improvements to a state-of-the-art grammar induction model using SDA and a slight modification to the parameterization of that model.</Paragraph>
    <Paragraph position="1"> These results support the case that annealing techniques in some cases offer performance gains over the standard EM approach to learning from unlabeled corpora, particularly with large corpora.</Paragraph>
  </Section>
class="xml-element"></Paper>