170 search results - page 7 / 34 » Online Large-Margin Training for Statistical Machine Transla... |
ECAI
2008
Springer
14 years 11 months ago
2008
Springer
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free"
FINTAL
2006
15 years 1 months ago
2006
Abstract. German compound words pose special problems to statistical machine translation systems: the occurence of each of the components in the training data is not sufficient for...
79
Voted
EMNLP
2010
14 years 7 months ago
2010
We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they a...
EMNLP
2010
14 years 7 months ago
2010
In modern machine translation practice, a statistical phrasal or hierarchical translation system usually relies on a huge set of translation rules extracted from bi-lingual traini...
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 ...