<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2230">
  <Title>Machine Translation with a Stochastic Grammatical Channel Dekai Wu and Hongsing WONG HKUST</Title>
  <Section position="10" start_page="1411" end_page="1411" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> Currently we are designing a tight generation-oriented Chinese grammar to replace our robust parsing-oriented grammar. We will use the new grammar to quantitatively evaluate objective 3. We are also studying complementary approaches to the English word deletion performed by wordskipping--i.e., extensions that insert Chinese words suggested by the target grammar into the output.</Paragraph>
    <Paragraph position="1"> The framework seeds a natural transition toward pattern-based translation models (objective 4). One 7These accuracy rates are relatively low because these experiments are being conducted with new lexicons and grammar on a new translation direction (English-Chinese).</Paragraph>
    <Paragraph position="2"> can post-edit the productions of a mirrored SITG more carefully and extensively than we have done in our cursory pruning, gradually transforming the original monolingual productions into a set of true transduction rule patterns. This provides a smooth evolution from a purely statistical model toward a hybrid model, as more linguistic resources become available.</Paragraph>
    <Paragraph position="3"> We have described a new stochastic grammatical channel model for statistical machine translation that exhibits several nice properties in comparison with Wu's SBTG model and IBM's word alignment model. The SITG-based channel increases translation speed, improves meaning-preservation accuracy, permits tight target CFGs to be incorporated for improving output grammaticality, and suggests a natural evolution toward transduction rule models. The input CFG is adapted for use via production mirroring, part-of-speech mapping, and wordskipping. We gave a polynomial-time translation algorithm that requires only a translation lexicon, plus a CFG and bigram language model for the target language. More linguistic knowledge about the target language is employed than in pure statistical translation models, but Wu's SBTG polynomial-time bound on search cost is retained and in fact the search space can be significantly reduced by using a good grammar. Output always conforms to the given target grammar.</Paragraph>
  </Section>
class="xml-element"></Paper>