<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1069">
  <Title>A Localized Prediction Model for Statistical Machine Translation</Title>
  <Section position="2" start_page="0" end_page="557" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper, we present a block-based model for statistical machine translation. A block is a pair of phrases which are translations of each other. For example, Fig. 1 shows an Arabic-English translation example that uses a8 blocks. During decoding, we view translation as a block segmentation process, where the input sentence is segmented from left to right and the target sentence is generated from bottom to top, one block at a time. A monotone block sequence is generated except for the possibility to swap a pair of neighbor blocks. We use an orientation model similar to the lexicalized block re-ordering model in (Tillmann, 2004; Och et al., 2004): to generate a block  where the Arabic words are romanized. The following orientation sequence is generated: a10 a18a73a72a75a74 a19 a10a77a76 a72a75a78 a19 a10a77a79 a72</Paragraph>
    <Paragraph position="2"> where a9 a24 is a block and a10 a24a83a82a85a84 a78 a14 efta21a12a19 a81 a14 ighta21a86a19 a74 a14 eutrala21a54a87 is a three-valued orientation component linked to the block a9 a24 (the orientation a10 a24a31a30 a18 of the predecessor block is currently ignored.). Here, the block sequence with orientation a14 a9a88a16a18 a19 a10 a16a18 a21 is generated under the restriction that the concatenated source phrases of the blocks a9 a24 yield the input sentence. In modeling a block sequence, we emphasize adjacent block neighbors that have Right or Left orientation. Blocks with neutral orientation are supposed to be less strongly 'linked' to their predecessor block and are handled separately. During decoding, most blocks have right orientation a14a12a10 a72a89a81 a21 , since the block translations are mostly monotone.</Paragraph>
    <Paragraph position="3">  The focus of this paper is to investigate issues in discriminative training of decoder parameters. Instead of directly minimizing error as in earlier work (Och, 2003), we decompose the decoding process into a sequence of local decision steps based on Eq. 1, and then train each local decision rule using convex optimization techniques.</Paragraph>
    <Paragraph position="4"> The advantage of this approach is that it can easily handle a large amount of features. Moreover, under this view, SMT becomes quite similar to sequential natural language annotation problems such as part-of-speech tagging, phrase chunking, and shallow parsing.</Paragraph>
    <Paragraph position="5"> The paper is structured as follows: Section 2 introduces the concept of block orientation bigrams. Section 3 describes details of the localized log-linear prediction model used in this paper. Section 4 describes the on-line training procedure and compares it to the well known perceptron training algorithm (Collins, 2002). Section 5 shows experimental results on an Arabic-English translation task. Section 6 presents a final discussion.</Paragraph>
  </Section>
class="xml-element"></Paper>