<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1022">
  <Title>Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation</Title>
  <Section position="7" start_page="172" end_page="173" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper we described a novel method of generating and applying hierarchical, dynamic topic-based language models. Specifically, we have proposed and evaluated hierarchical cluster generation procedures that yield specially balanced and pruned trees directly optimized for language modeling purposes. We also present a novel hierarchical interpolation algorithm for generating a language model from these trees, specializing in the hierarchical topic-conditional probability estimation for a target topic-sensitive vocabulary (34% of the entire vocabulary). We also propose and evaluate a range of dynamic topic detection procedures based on several transformations of content-vector similarity measures. These dynamic estimations of P(topici\[history) are combined with the hierarchical estimation of P(wordj Itopici, history) in a product across topics, yielding a final probability estimate  of P(wordj Ihistory) that effectively captures long-distance lexical dependencies via these intermediate topic models. Statistically significant reductions in perplexity are obtained relative to a baseline model, both on the entire text (10.5%) and on the target vocabulary (33.5%). This large improvement on a readily isolatable subset of the data bodes well for further model combination.</Paragraph>
  </Section>
class="xml-element"></Paper>