<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1003">
  <Title>Improved Statistical Machine Translation Using Paraphrases</Title>
  <Section position="8" start_page="23" end_page="23" type="concl">
    <SectionTitle>
7 Discussion
</SectionTitle>
    <Paragraph position="0"> In this paper we have shown that significant gains in coverage and translation quality can be had by integrating paraphrases into statistical machine translation. In effect, paraphrases introduce some amount of generalization into statistical machine translation.</Paragraph>
    <Paragraph position="1"> Whereas before we relied on having observed a particular word or phrase in the training set in order to produce a translation of it, we are no longer tied to having seen every word in advance. We can exploit knowledge that is external to the translation model about what words have similar meanings and use that in the process of translation. This method is particularly pertinent to small data conditions, which are plagued by sparse data problems.</Paragraph>
    <Paragraph position="2"> In future work, we plan to determine how much data is required to learn useful paraphrases. The scenario described in this paper was very favorable to creating high quality paraphrases. The large number of parallel corpora between Spanish and the other languages present in the Europarl corpus allowed us to generate high quality, in domain data. While this is a realistic scenario, in that many new official languages have been added to the European Union, some of which do not yet have extensive parallel corpora, we realize that this may be a slightly idealized scenario.</Paragraph>
    <Paragraph position="3"> Finally, we plan to formalize our targeted manual evaluation method, in the hopes of creating a evaluation methodology for machine translation that is more thorough and elucidating than Bleu.</Paragraph>
  </Section>
class="xml-element"></Paper>