<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1102">
  <Title>A Practical Text Summarizer by Paragraph Extraction for Thai</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper, we have presented a practical approach to Thai text summarization by extracting the  pression rate 30%.</Paragraph>
    <Paragraph position="1"> most relevant paragraphs from the original document. Our approach takes advantage of both the local and global properties of paragraphs. The algorithm that combines these two properties for ranking and extracting paragraphs is given. Furthermore, the algorithm does not require the external knowledge other than the document itself, and be able to summarize general text documents.</Paragraph>
    <Paragraph position="2"> In future work, we intend to conduct experiments with different document genres. We continue to further develop standard data sets for evaluating Thai text summarization system. Many research questions remain. Since extraction performs at the paragraph level, the paragraph lengths may affect the summarization results. The recent approach for editing extracted text spans (Jing and McKeown, 2000) may also produce improvement for our algorithm. We believe that our algorithm is languageindependent, which can summarize documents written in many other languages. We plan to experimentally test our algorithm with available standard data sets in English.</Paragraph>
  </Section>
class="xml-element"></Paper>