<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1063">
  <Title>Term Recognition Using Technical Dictionary Hierarchy</Title>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
1 Method Description
</SectionTitle>
    <Paragraph position="0"> The description of the proposed method is shown in figure 1. There are three main steps in our method. In the first stage, candidate terms that are complex nominal are extracted by a linguistic filter and a dictionary hierarchy is constructed. In the second stage, candidate terms are scored by each weighting scheme. In dictionary weighing scheme, candidate terms are scored based on the kind of domain dictionary where terms appear. In statistical weighting scheme, terms are scored by their frequency in the given corpus. In transliterated word weighting scheme, terms are scored by the number of transliterated foreign words in the terms. In the third stage, each weight is normalized and combined to Term weight</Paragraph>
  </Section>
class="xml-element"></Paper>