<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1031">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Feedback-Augmented Method for Detecting Errors in the Writing of Learners of English</Title>
  <Section position="8" start_page="247" end_page="247" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper has proposed a feedback-augmented method for distinguishing mass and count nouns to complement the conventional rules for detecting grammatical errors. The experiments have shown that the proposed method detected 71% of the target errors in the writing of Japanese learners of English with a precision of 72% when it was augmented by feedback. From the results, we conclude that the feedback-augmented method is effective to detecting errors concerning the articles and singular plural usage in the writing of Japanese learners of English.</Paragraph>
    <Paragraph position="1"> Although it is not taken into account in this paper, the feedback corpus contains further useful information. For example, we can obtain training data consisting of instances of errors by comparing the feedback corpus with its original corpus. Also, comparing it with the results of detection, we can know performance of each rule used in the detection, which make it possible to increase or decrease their log-likelihood ratios according to their performance. We will investigate how to exploit these sources of information in future work.</Paragraph>
  </Section>
class="xml-element"></Paper>