133 search results - page 8 / 27 » Joint Tokenization and Translation |
ACL
2012
13 years 2 months ago
2012
With a few exceptions, discriminative training in statistical machine translation (SMT) has been content with tuning weights for large feature sets on small development data. Evid...
127
click to vote
EMNLP
2011
13 years 11 months ago
2011
We present an online learning algorithm for training parsers which allows for the inclusion of multiple objective functions. The primary example is the extension of a standard sup...
IJPRAI
2002
14 years 11 months ago
2002
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...
ACL
2010
14 years 9 months ago
2010
We present a novel approach to integrate transliteration into Hindi-to-Urdu statistical machine translation. We propose two probabilistic models, based on conditional and joint pr...
BMVC
1996
15 years 1 months ago
1996
This paperdescribes initial work on a family of projectivereconstructiontechniques that extract projection matrices directly and linearly from matching tensors estimated from imag...