<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1019">
  <Title>A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
TEMPLATE
SEQUENCE
MODEL
PERMUTATION
MODEL
PHRASE
PHRASAL
TRANSLATION
MODEL
TARGET
LANGUAGE MODEL
</SectionTitle>
    <Paragraph position="0"> eration of lattices or N-best lists of bitext word alignment or translation hypotheses.</Paragraph>
    <Paragraph position="1"> Weighted Finite State Transducers for Statistical Machine Translation (SMT) have been proposed in the literature to implement word-to-word translation models (Knight and Al-Onaizan, 1998) or to perform translation in an application domain such as the call routing task (Bangalore and Ricardi, 2001). One of the objectives of these approaches has been to provide an implementation for SMT that uses standard FSM algorithms to perform model computations and therefore make SMT techniques accessible to a wider community. Our WFST implementation of the ATTM has been developed with similar objectives.</Paragraph>
    <Paragraph position="2"> We start off by presenting a derivation of the ATTM that identifies the conditional independence assumptions that underly the model. The derivation allows us to specify each component distribution of the model and implement it as a weighted finite state transducer. We then show that bitext word alignment and translation can be performed with standard FSM operations involving these transducers. Finally we report bitext word alignment and translation performance of the implementation on the</Paragraph>
  </Section>
class="xml-element"></Paper>