283 search results - page 10 / 57 » Improving Statistical Word Alignment with Ensemble Methods |
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...
AI
2009
Springer
14 years 2 months ago
2009
Springer
Despite the impressive amount of recent studies devoted to improving the state of the art of Machine Translation (MT), Computer Assisted Translation (CAT) tools remain the preferre...
SDM
2008
SIAM
13 years 9 months ago
2008
SIAM
This paper studies the ensemble selection problem for unsupervised learning. Given a large library of different clustering solutions, our goal is to select a subset of solutions t...
IBPRIA
2003
Springer
14 years 20 days ago
2003
Springer
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
COLING
2008
13 years 9 months ago
2008
The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confusion networks. One of the crucial steps in confusion network d...