<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1003">
  <Title>Improvement of a Whole Sentence Maximum Entropy Language Model Using Grammatical Featuresa0</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> In this work, we have sucessfully added grammatical features to a WSME language model using a SCFG to extract the grammatical information. We have shown that the the use of grammatical features in a WSME model improves the performance of the model. Adding grammatical features to the WSME model we have obtained a reduction in perplexity of 13% on average over models that do not use grammatical features. Also a reduction in perplexity between approximately 22% and 28% over the n-gram model has been obtained.</Paragraph>
    <Paragraph position="1"> We are working on the implementation of other kinds of grammatical features which are based on the POStags sentences obtained using the SCFG that we have defined. The prelimary experiments have shown promising results.</Paragraph>
    <Paragraph position="2"> We will also be working on the evaluation of the word-error rate (WER) of the WSME model.</Paragraph>
    <Paragraph position="3"> In the case of WSME model the WER may be evaluated in a type of post-procesing using the n-best utterances.</Paragraph>
  </Section>
class="xml-element"></Paper>