2075 search results - page 98 / 415 » Learning better transliterations |
128
click to vote
NAACL
2007
15 years 5 months ago
2007
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
142
click to vote
NAACL
2004
15 years 5 months ago
2004
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
138
click to vote
IMCSIT
2010
15 years 2 months ago
2010
Abstract--We present a method for improving existing statistical machine translation methods using an knowledge-base compiled from a bilingual corpus as well as sequence alignment ...
141
click to vote
IWANN
1999
Springer
15 years 8 months ago
1999
Springer
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
173
click to vote
ICRA
2010
IEEE
15 years 3 months ago
2010
IEEE
— In recent years, learning models from data has become an increasingly interesting tool for robotics, as it allows straightforward and accurate model approximation. However, in ...