1233 search results - page 68 / 247 » N-gram-based Machine Translation |
EMNLP
2009
14 years 9 months ago
2009
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
EMNLP
2006
15 years 1 months ago
2006
We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a bet...
ACL
2003
15 years 1 months ago
2003
We augment a model of translation based on re-ordering nodes in syntactic trees in order to allow alignments not conforming to the original tree structure, while keeping computati...
111
click to vote
ACL
2012
13 years 2 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
2009
14 years 9 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...