<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1064">
  <Title>A SNoW based Supertagger with Application to NP Chunking</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have proposed the use of supertags in the NP chunking task in order to use more syntactical dependencies which are unavailable with POS tags. In order to train a supertagger with a larger context, we have proposed a novel method of applying SNoW to the sequential model and have applied it to supertagging. Our algorithm takes advantage of rich feature sets, avoids the sparse-data problem, and forces the learning algorithm to focus on the difficult cases.</Paragraph>
    <Paragraph position="1"> Being aware of the fact that our algorithm may suffer from the label bias problem, we have used two methods to cope with this problem, and achieved desirable results.</Paragraph>
    <Paragraph position="2"> We have tested our algorithms on both the hand-coded tag set used in (Chen et al., 1999) and supertags extracted for Penn Treebank(PTB). On the same dataset as that of (Chen et al., 1999), our new supertagger achieves an accuracy of a2a4a3a6a5a8a7a10a9a12a11 . Compared with the supertaggers with the same decoding complexity (Chen, 2001), our algorithm achieves an error reduction of a22a23a5a26a9a12a11 .</Paragraph>
    <Paragraph position="3"> We repeat Ramshaw and Marcus' Transformation Based NP chunking (Ramshaw and Marcus, 1995) test by substituting supertags for POS tags in the dataset. The use of supertags in NP chunking gives rise to almost a9a12a11 absolute increase (from a2a4a3a6a5a14a13a16a15a16a11 to a2a4a3a6a5a17a2a4a18a16a11 ) in F-score under Transformation Based Learning(TBL) frame, or an error reduction of a9a4a9a21a5a17a140a16a11 .</Paragraph>
    <Paragraph position="4"> The accuracy of a2a4a3a6a5a17a2a4a18a16a11 with our individual TBL chunker is close to results of POS-tag-based systems using advanced machine learning algorithms, such as a2a4a15a6a5a17a15a65a7a23a11 by voted MBL chunkers (Sang, 2002), a2a4a3a6a5a17a140a16a11 by SNoW chunker (Mu~noz et al., 1999). The benefit of using a supertagger is obvious. The supertagger provides an opportunity for advanced machine learning techniques to improve their performance on chunking tasks by exploiting more syntactic information encoded in the supertags.</Paragraph>
    <Paragraph position="5"> To sum up, the supertagging algorithm presented here provides an effective and efficient way to employ syntactic information.</Paragraph>
  </Section>
class="xml-element"></Paper>