<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0707">
  <Title>Memory-Based Shallow Parsing</Title>
  <Section position="3" start_page="58" end_page="58" type="concl">
    <SectionTitle>
Conclusion
</SectionTitle>
    <Paragraph position="0"> We have developed and empirically tested a memory-based learning (MBL) approach to shallow parsing in which POS tagging, chunking, and identification of syntactic relations are formulated as memory-based modules. A learning approach to shallow parsing allows for fast development of modules with high coverage, robustness, and adaptability to different sublanguages.</Paragraph>
    <Paragraph position="1"> The memory-based algorithms we used (IBI-IG and IGTrtEE) are simple and efficient supervised learning algorithms. Our approach was evaluated on NP and VP chunking, and subject/object detection (using output from the clmnker). Fa=l scores are 93.8% for NP chunking, 94.7% for VP chunking, 77.1% for subject detection and 79.0% for object detection. The accuracy and efficiency of the approach are encouraging (no optimisation or post-processing of any kind was used yet), and comparable to or better than state-of-the-art alternative learning methods.</Paragraph>
    <Paragraph position="2"> We also extensively compared our approach to a recently proposed new memory-based learning algorithm, memory-based sequence learning (MBSL, \[Argamon et al., 1998\] and showed that MBL, which is a computationally simpler algorithm than MBSL, is able to readl similar precision and recall when restricted to the MBSL definition of the NP chunking, subject detection and object detection tasks. More importantly, MBL is more flexible in the definition of the shallow parsingtasks: it allows nested relations to be detected; it allows the addition and integration into the task of various additional sources of information apart from POS tags; it can segment a tagged sentence into different types of constituent chunks in one pass; it can scan a chunked sentence for different relation types in one pass (though separating subject-verb detection from object-verb detection is surely an option that must be investigated).</Paragraph>
    <Paragraph position="3"> In current research we are extending the approach to other types of constituent chunks and other types of syntactic relations. Combined with previous results on PP-attachment \[Zavrel et al., 1997\], the results presented here will be integrated into a complete shallow parser.</Paragraph>
  </Section>
class="xml-element"></Paper>