1991 search results - page 38 / 399 » Small Models of Large Machines |
FGCS
2006
14 years 9 months ago
2006
Some of the most challenging applications to parallelize scalably are the ones that present a relatively small amount of computation per iteration. Multiple interacting performanc...
EMNLP
2007
14 years 11 months ago
2007
We present a method for improving word alignment for statistical syntax-based machine translation that employs a syntactically informed alignment model closer to the translation m...
COLING
2010
14 years 4 months ago
2010
We present an adaptation technique for statistical machine translation, which applies the well-known Bayesian learning paradigm for adapting the model parameters. Since state-of-t...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
In EM and related algorithms, E-step computations distribute easily, because data items are independent given parameters. For very large data sets, however, even storing all of th...
101
click to vote
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
Supervised learning is difficult with high dimensional input spaces and very small training sets, but accurate classification may be possible if the data lie on a low-dimensional ...