<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2086">
  <Title>URES : an Unsupervised Web Relation Extraction System</Title>
  <Section position="7" start_page="672" end_page="672" type="concl">
    <SectionTitle>
5 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented the URES system for autonomously extracting relations from the Web.</Paragraph>
    <Paragraph position="1"> URES bypasses the bottleneck created by classic information extraction systems that either relies on manually developed extraction patterns or on manually tagged training corpus. Instead, the system relies upon learning patterns from a large unlabeled set of sentences downloaded from Web.</Paragraph>
    <Paragraph position="2"> One of the topics we would like to further explore is the complexity of the patterns that we learn. Currently we use a very simple pattern language that just has 4 types of elements, slots, constants and two types of skips. We want to see if we can achieve higher precision with more complex patterns. In addition we would like to test URES on n-ary predicates, and to extend the system to handle predicates that are allowed to lack some of the attributes.</Paragraph>
  </Section>
class="xml-element"></Paper>