216 search results - page 10 / 44 » Improvements in Phrase-Based Statistical Machine Translation |
EMNLP
2009
14 years 7 months ago
2009
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
NAACL
2010
14 years 7 months ago
2010
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
LREC
2008
14 years 11 months ago
2008
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
EMNLP
2007
14 years 11 months ago
2007
We show for the first time that incorporating the predictions of a word sense disambiguation system within a typical phrase-based statistical machine translation (SMT) model cons...
COLING
2010
14 years 4 months ago
2010
Syntax based reordering has been shown to be an effective way of handling word order differences between source and target languages in Statistical Machine Translation (SMT) syste...