<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1121">
  <Title>POS Tagging versus Classes in Language Modeling</Title>
  <Section position="7" start_page="186" end_page="186" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we presented a POS-based language model. Unlike previous approaches that use POS tags in language modeling, we redefine the speech recognition problem so that it includes finding the best word sequence and best POS tag interpretation for those words. Thus this work can be seen as a first-step towards tightening the integration between speech recognition and natural language processing.</Paragraph>
    <Paragraph position="1"> In order to make use of the POS tags, we use a decision tree algorithm to learn the probability distributions, and a clustering algorithm to build hierarchical partitionings of the POS tags and the word identities. Furthermore, we take advantage of the POS tags in building the word classification trees and in estimating the word probabilities, which both results in better performance and significantly speeds up the training procedure. We find that using the rich context afforded by decision tree results in a perplexity reduction of 44.4%. We also find that the POS-based model gives a 4.2% reduction in perplexity over a class-based model, also built with the decision tree and clustering algorithms. Preliminary results on the Wall Street Journal corpus are also encouraging. Hence, using a POS-based model results in an improved language model as well as accomplishes the first part of the task in linguistic understanding.</Paragraph>
    <Paragraph position="2"> We also see that using POS tags in the language model aids in the identification of boundary tones and speech repairs, which we have also incorporated into the model by further redefining the speech recognition problem. The POS tags allow these two processes to generalize about the syntactic role that words are playing in the utterance rather than using crude class-based approaches which does not distinguish this information. We also see that modeling these phenomena improves the POS tagging results as well as the word perplexity.</Paragraph>
  </Section>
class="xml-element"></Paper>