<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0404">
  <Title>Using Semantic and Syntactic Graphs for Call Classi cation</Title>
  <Section position="6" start_page="30" end_page="30" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have introduced syntactic and semantic graphs (SSGs) for speech and language processing. We have described their use for the task of call classi cation. We have presented results showing 4.74% improvement, using utterances collected from AT&amp;T VoiceTone spoken dialog system. SSGs can also be useful for text classi cation and other similar language processing applications. Our future work includes feature selection prior to classi cation and developing methods that are more robust to ASR errors while computing the SSGs. We also plan to improve the syntactic and semantic processing components by adapting the models with some amount of labeled in-domain spoken dialog data.</Paragraph>
  </Section>
class="xml-element"></Paper>