<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3116">
  <Title>Mood at work: Ramses versus Pharaoh</Title>
  <Section position="2" start_page="0" end_page="126" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Phrase-based (PB) machine translation (MT) is now a popular paradigm, partly because of the relative ease with which we can automatically create an acceptable translation engine from a bitext. As a matter of fact, deriving such an engine from a bitext consists in (more or less) gluing together dedicated software modules, often freely available. Word-based models, or the so-called IBM models, can be trained using the GIZA or GIZA++ toolkits (Och and Ney, 2000). One can then train phrase-based models using the THOT toolkit (Ortiz-Mart'inez et al., 2005).</Paragraph>
    <Paragraph position="1"> For their part, language models currently in use in SMT systems can be trained using packages such as SRILM (Stolcke, 2002) and the CMU-SLM toolkit (Clarkson and Rosenfeld, 1997).</Paragraph>
    <Paragraph position="2">  baseline.html Once all the models are built, one can choose to use PHARAOH (Koehn, 2004), an efficient full-fledged phrase-based decoder. We only know of one major drawback when using PHARAOH: its licensing policy. Indeed, it is available for non-commercial use in its binary form only. This severely limits its use, both commercially and scientifically (Walker, 2005).</Paragraph>
    <Paragraph position="3"> For this reason, we undertook the design of a generic architecture called MOOD (Modular Object-Oriented Decoder), especially suited for instantiating SMT decoders. Two major goals directed our design of this package: offering open source, state-of-the-art decoders and providing an architecture to easily build these decoders. This effort is described in (Patry et al., 2006).</Paragraph>
    <Paragraph position="4"> As a proof of concept that our framework (MOOD) is viable, we attempted to use its functionalities to implement a clone of PHARAOH, based on the comprehensive user manual of the latter. This clone, called RAMSES, is now part of the MOOD distribution, which can be downloaded freely from the page http://smtmood.sourceforge.net.</Paragraph>
    <Paragraph position="5"> We conducted a pair-to-pair comparison between the two engines that we describe in this paper. We provide an overview of the MOOD architecture in Section 2. Then we describe briefly RAMSES in Section 3. The comparison between the two decoders in terms of automatic metrics is analyzed in Section 4. We confirm this comparison by presenting a manual evaluation we conducted on an random sample of the translations produced by both decoders. This is reported in Section 5. We conclude in Section 6.</Paragraph>
  </Section>
class="xml-element"></Paper>