118 search results - page 18 / 24 » Unlabeled data improves word prediction |
131
Voted
ACL
2011
14 years 3 months ago
2011
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
100
Voted
PKDD
2010
Springer
14 years 9 months ago
2010
Springer
A heterogeneous information network is a network composed of multiple types of objects and links. Recently, it has been recognized that strongly-typed heterogeneous information net...
ICML
2007
IEEE
16 years 14 days ago
2007
IEEE
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
98
Voted
HPCA
2006
IEEE
15 years 5 months ago
2006
IEEE
Caches are very inefficiently utilized because not all the excess data fetched into the cache, to exploit spatial locality, is utilized. We define cache utilization as the percent...
IJON
2010
14 years 10 months ago
2010
We present an EM-algorithm for the problem of learning preferences with Gaussian processes in the context of multi-task learning. We validate our approach on an audiological data ...