<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1083">
  <Title>Statistical Machine Translation by Parsing</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper has presented generalizations of ordinary parsing that emerge when the grammar and/or the input can be multidimensional. Along the way, it has elucidated the relationships between ordinary parsers and other classes of algorithms, some previously known and some not. It turns out that, given some multitext and a monolingual treebank, a rudimentary multitree-based statistical machine translation system can be built and applied using only generalized parsers and some trivial glue.</Paragraph>
    <Paragraph position="1"> There are three research benefits of using generalized parsers to build MT systems. First, we can  take advantage of past and future research on making parsers more accurate and more efficient. Therefore, second, we can concentrate our efforts on better models, without worrying about MT-specific search algorithms. Third, more generally and most importantly, this approach encourages MT research to be less specialized and more transparently related to the rest of computational linguistics.</Paragraph>
  </Section>
class="xml-element"></Paper>