An augmented three-pass system combination framework: DCU combination system for WMT 2010
Way, AndyORCID: 0000-0001-5736-5930, Pecina, Pavel and Du, JinhuaORCID: 0000-0002-3267-4881
(2010)
An augmented three-pass system combination framework: DCU combination system for WMT 2010.
In: WMT 2010 - The Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR, ACL 2010, 15-16 July 2010, Uppsala, Sweden.
This paper describes the augmented threepass
system combination framework of
the Dublin City University (DCU) MT
group for the WMT 2010 system combination
task. The basic three-pass framework
includes building individual confusion
networks (CNs), a super network, and
a modified Minimum Bayes-risk (mCon-
MBR) decoder. The augmented parts for
WMT2010 tasks include 1) a rescoring
component which is used to re-rank the
N-best lists generated from the individual
CNs and the super network, 2) a new hypothesis
alignment metric – TERp – that
is used to carry out English-targeted hypothesis
alignment, and 3) more different
backbone-based CNs which are employed
to increase the diversity of the
mConMBR decoding phase. We took
part in the combination tasks of Englishto-
Czech and French-to-English. Experimental
results show that our proposed
combination framework achieved 2.17 absolute
points (13.36 relative points) and
1.52 absolute points (5.37 relative points)
in terms of BLEU score on English-to-
Czech and French-to-English tasks respectively
than the best single system. We
also achieved better performance on human
evaluation.