<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1038">
  <Title>Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text</Title>
  <Section position="3" start_page="296" end_page="296" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> This work can be viewed as a step toward the integration of information extraction and data mining technology, a direction of growing interest. Nahm and Mooney (2000) present a system that mines association rules from a database constructed from automaticallyextracteddata,thenappliestheselearned null rules to improve data field recall without revisiting the text. Our work attempts to more tightly integrate the extraction and mining tasks by learning relational patterns that can be included probabilistically into extraction to improve its accuracy; also, our work focuses on mining from relational graphs, rather than single-table databases.</Paragraph>
    <Paragraph position="1"> McCallum and Jensen (2003) argue the theoretical benefits of an integrated probabilistic model for extraction and mining, but do not construct such a system. Our work is a step in the direction of their proposal, using an inference procedure based on a closed-loop iteration between extraction and relational pattern discovery.</Paragraph>
    <Paragraph position="2"> Mostotherworkinthisareaminesrawtext, rather than a database automatically populated via extraction (Hearst, 1999; Craven et al., 1998).</Paragraph>
    <Paragraph position="3"> This work can also be viewed as part of a trend to perform joint inference across multiple language processing tasks (Miller et al., 2000; Roth and tau Yih, 2002; Sutton and McCallum, 2004).</Paragraph>
    <Paragraph position="4"> Finally, using relational paths between entities is also examined in (Richards and Mooney, 1992) to escapelocalmaximainafirst-orderlearningsystem.</Paragraph>
  </Section>
class="xml-element"></Paper>