Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation
Venue
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp. 620-629
Publication Year
2008
Authors
Roy Tromble, Shankar Kumar, Franz Och, Wolfgang Macherey
BibTeX
Abstract
We present Minimum Bayes-Risk (MBR) decoding over translation lattices that
compactly encode a huge number of translation hypotheses. We describe conditions on
the loss function that will enable efficient implementation of MBR decoders on
lattices. We introduce an approximation to the BLEU score~\cite{papineni01} that
satisfies these conditions. The MBR decoding under this approximate BLEU is
realized using Weighted Finite State Automata. Our experiments show that the
Lattice MBR decoder yields moderate, consistent gains in translation performance
over N-best MBR decoding on Arabic-to-English, Chinese-to-English and
English-to-Chinese translation tasks. We conduct a range of experiments to
understand why Lattice MBR improves upon N-best MBR and also study the impact of
various parameters on MBR performance.
