<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-1004">
  <Title>Computational Complexity of Statistical Machine Translation</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In this paper we study a set of problems that are of considerable importance to Statistical Machine Translation (SMT) but which have not been addressed satisfactorily by the SMT research community.</Paragraph>
    <Paragraph position="1"> Over the last decade, a variety of SMT algorithms have been built and empirically tested whereas little is known about the computational complexity of some of the fundamental problems of SMT. Our work aimsat providing useful insights into the the computational complexity of those problems. We prove that while IBM Models 1-2 are conceptually and computationally simple, computations involving the higher (and more useful) models are hard.</Paragraph>
    <Paragraph position="2"> Since it is unlikely that there exists a polynomial time solution for any of these hard problems (unless P = NP and P#P = P), our results highlight and justify the need for developing polynomial time approximations for these computations. We also discuss some practical ways of dealing with complexity.</Paragraph>
  </Section>
class="xml-element"></Paper>