<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1049">
  <Title>A Report of Recent Progress in Transformation-Based Error-Driven Learning*</Title>
  <Section position="3" start_page="256" end_page="256" type="intro">
    <SectionTitle>
2. TRANSFORMATION-BASED
ERROR-DRIVEN LEARNING
</SectionTitle>
    <Paragraph position="0"> Transformation-based error-driven learning has been applied to a number of natural language problems, including part of speech tagging, prepositional phrase attachment disambiguation, and syntactic parsing \[Brill 92, Brill 93, Brill 93a\]. A similar approach is being explored for machine translation \[Su et al. 92\]. Figure 1 illustrates the learning process. First, unannotated text is passed through the initial-state annotator. The initial-state annotator can range in complexity from assigning random structure to assigning the output of a sophisticated manually created annotator. Once text has been passed through the initial-state annotator, it is then compared to the truth, 3 and transformations are learned that can be applied to the output of the initial state annotator to make it better resemble the truth.</Paragraph>
    <Paragraph position="1"> In all of the applications described in this paper, the following greedy search is applied: at each iteration of learning, the transformation is found whose application resuits in the highest score; that transformation is then added to the ordered transformation list and the training corpus is updated by applying the learned transformation. To define a specific application of transformation-</Paragraph>
  </Section>
class="xml-element"></Paper>