<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1078">
  <Title>discriminative named entity recognition of speech data</Title>
  <Section position="9" start_page="622" end_page="623" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We proposed a method for NER of speech data that incorporates ASR confidence as a feature of discriminative NER, where the NER model  is trained using both text-based and ASR-based training data. In experiments using SVMs, the proposed method showed a higher NER Fmeasure, especially in terms of improving precision, than simply applying text-based NER to ASR results. The method effectively rejected erroneous NEs due to ASR errors with a small drop of recall, thanks to both the ASR confidence feature and ASR-based training data. NER-level rejection also effectively increased precision.</Paragraph>
    <Paragraph position="1"> Our approach can also be used in other tasks in spoken language processing, and we expect it to be effective. Since confidence itself is not limited to speech, our approach can also be applied to other noisy inputs, such as optical character recognition (OCR). For further improvement, we will consider N-best ASR results or word lattices as inputs and introduce more speech-specific features such as word durations and prosodic features.</Paragraph>
    <Paragraph position="2"> Acknowledgments We would like to thank anonymous reviewers for their helpful comments.</Paragraph>
  </Section>
class="xml-element"></Paper>