<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1038">
  <Title>Discriminative Training and Maximum Entropy Models for Statistical Machine Translation</Title>
  <Section position="7" start_page="0" end_page="0" type="relat">
    <SectionTitle>
6 Related Work
</SectionTitle>
    <Paragraph position="0"> The use of direct maximum entropy translation models for statistical machine translation has been sug- null mum entropy training for alignment templates; ,1: trigram language model; ,2: alignment template model, ,3: lexicon model, ,4: alignment model (normalized such that P4m=1 ,m = 4).</Paragraph>
    <Paragraph position="1">  gested by (Papineni et al., 1997; Papineni et al., 1998). They train models for natural language understanding rather than natural language translation. In contrast to their approach, we include a dependence on the hidden variable of the translation model in the direct translation model. Therefore, we are able to use statistical alignment models, which have been shown to be a very powerful component for statistical machine translation systems.</Paragraph>
    <Paragraph position="2"> In speech recognition, training the parameters of the acoustic model by optimizing the (average) mutual information and conditional entropy as they are defined in information theory is a standard approach (Bahl et al., 1986; Ney, 1995). Combining various probabilistic models for speech and language modeling has been suggested in (Beyerlein, 1997; Peters and Klakow, 1999).</Paragraph>
  </Section>
class="xml-element"></Paper>