<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0823">
  <Title>Statistical Machine Translation of Euparl Data by using Bilingual N-grams</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> During the last decade, statistical machine translation (SMT) systems have evolved from the original word-based approach (Brown et al., 1993) into phrase-based translation systems (Koehn et al., 2003). Similarly, the noisy channel approach has been expanded to a more general maximum entropy approach in which a log-linear combination of multiple models is implemented (Och and Ney, 2002).</Paragraph>
    <Paragraph position="1"> The SMT approach used in this work implements a log-linear combination of feature functions along with a translation model which is based on bilingual n-grams. This translation model was developed by de Gispert and Mari~no (2002), and it differs from the well known phrase-based translation model in two basic issues: first, training data is monotonously segmented into bilingual units; and second, the model considers n-gram probabilities instead of relative frequencies. This model is described in section 2.</Paragraph>
    <Paragraph position="2"> Translation results from the four source languages made available for the shared task (es: Spanish, fr: French, de: German, and fi: Finnish) into English (en) are presented and discussed.</Paragraph>
    <Paragraph position="3"> The paper is structured as follows. Section 2 describes the bilingual n-gram translation model. Section 3 presents a brief overview of the whole SMT procedure. Section 4 presents and discusses the shared task results and other interesting experimentation. Finally, section 5 presents some conclusions and further work.</Paragraph>
  </Section>
class="xml-element"></Paper>