<?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="3" start_page="1408" end_page="1408" type="intro">
    <SectionTitle>
2 Review: Noisy Channel Model
</SectionTitle>
    <Paragraph position="0"> The statistical translation model introduced by IBM (Brown et al., 1990) views translation as a noisy channel process. The underlying generative model contains a stochastic Chinese (input) sentence generator whose output is &amp;quot;corrupted&amp;quot; by the translation channel to produce English (output) sentences.</Paragraph>
    <Paragraph position="1"> Assume, as we do throughout this paper, that the input language is English and the task is to translate into Chinese. In the IBM system, the language model employs simple n-grams, while the translation model employs several sets of parameters as discussed below. Estimation of the parameters has been described elsewhere (Brown et al., 1993).</Paragraph>
    <Paragraph position="2"> Translation is performed in the reverse direction from generation, as usual for recognition under generative models. For each English sentence e to be translated, the system attempts to find the Chinese sentence c, such that:</Paragraph>
    <Paragraph position="4"> In the IBM model, the search for the optimal c, is performed using a best-first heuristic &amp;quot;stack search&amp;quot; similar to A* methods.</Paragraph>
    <Paragraph position="5"> One of the primary obstacles to making the statistical translation approach practical is slow speed of translation, as performed in A* fashion. This price is paid for the robustness that is obtained by using very flexible language and translation models. The language model allows sentences of arbitrary order and the translation model allows arbitrary word-order permutation. No structural constraints and explicit linguistic grammars are imposed by this model.</Paragraph>
    <Paragraph position="6"> The translation channel is characterized by two sets of parameters: translation and alignment probabilities, l The translation probabilities describe lexical substitution, while alignment probabilities describe word-order permutation. The key problem is that the formulation of alignment probabilities a(ilj , V, T) permits the English word in position j of a length-T sentence to map to any position i of a length-V Chinese sentence. So V T alignments are possible, yielding an exponential space with correspondingly slow search times.</Paragraph>
    <Paragraph position="7"> I Various models have been constructed by the IBM team (Brown et al., 1993). This description corresponds to one of the simplest ones, &amp;quot;Model 2&amp;quot;; search costs for the more complex models are correspondingly higher.</Paragraph>
  </Section>
class="xml-element"></Paper>