Sciweavers

12 search results - page 3 / 3
» Exploiting Parallel Treebanks to Improve Phrase-Based Statis...
Sort
View
ECIR
2010
Springer
13 years 6 months ago
Estimating Translation Probabilities from the Web for Structured Queries on CLIR
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...
Xabier Saralegi, Maddalen Lopez de Lacalle
EMNLP
2008
13 years 6 months ago
Online Large-Margin Training of Syntactic and Structural Translation Features
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
David Chiang, Yuval Marton, Philip Resnik