Friday, May 23, 2008
12:30 PM
CSB 703
Ding Liu
University of Rochester
Improved Tree-to-string Transducer for Machine Translation
We propose three enhancements to the tree-to-string (TTS) transducer for
machine translation:
first-level expansion-based normalization
for TTS templates, a syntactic alignment
framework integrating the insertion of
unaligned target words, and a subtree-based ngram
model addressing the tree decomposition
probability. Empirical results show that
these methods improve the performance of a
TTS transducer based on the standard BLEU-4 metric. We also experiment with
semantic
labels in a TTS transducer, and achieve improvement
over our baseline system.