<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-2041">
  <Title>Learning Non-Isomorphic Tree Mappings for Machine Translation</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Often one may wish to learn a tree-to-tree mapping, training it on unaligned pairs of trees, or on a mixture of trees and strings.</Paragraph>
    <Paragraph position="1"> Unlike previous statistical formalisms (limited to isomorphic trees), synchronous TSG allows local distortion of the tree topology. We reformulate it to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.</Paragraph>
  </Section>
class="xml-element"></Paper>