561 search results - page 22 / 113 » Randomised Language Modelling for Statistical Machine Transl... |
EMNLP
2009
13 years 5 months ago
2009
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
SIGIR
2010
ACM
13 years 11 months ago
2010
ACM
As a principled approach to capturing semantic relations of words in information retrieval, statistical translation models have been shown to outperform simple document language m...
MT
2006
13 years 7 months ago
2006
We describe a novel approach to machine translation that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed d...
ACL
2012
11 years 10 months ago
2012
Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
EMNLP
2004
13 years 9 months ago
2004
We describe experiments carried out with adaptive language and translation models in the context of an interactive computer-assisted translation program. We developed cache-based ...