<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0109">
  <Title>I ! Corpus Based PP Attachment Ambiguity Resolution 1 with a Semantic Dictionary II</Title>
  <Section position="10" start_page="78" end_page="78" type="concl">
    <SectionTitle>
6. CONCLUSION AND FURTHER WORK
</SectionTitle>
    <Paragraph position="0"> The most cor0putationally expensive part of the system is the word sense disambiguation of the training corpus. This, however, is done only once and the disarnbiguated corpus is stored for future classifications of unseen quadruples. The above experiments confirmed the expectations that using the semantic information in combination with even a very limited context leads to a substantial improvement of NLP techniques. Although our method exhibits an accuracy close to the human performance, we feel that there is still a space for improvement, particularly in using a wider sentential context (human performance on full sentential context is over 93%), more training data and/or more accurate sense disambiguation technique. We believe that there is further space for elaboration of our method, in particular, it would be interesting to know the exact relations between the accuracy and the termination condition, and between the corpus size and the optimum termination condition separately for each preposition. At the moment, we are working on an implementation of the algorithm to work on with a wider sentential context and on its incorporation within a more complex NLP system.</Paragraph>
  </Section>
class="xml-element"></Paper>