47 search results - page 3 / 10 » Discriminative Word Alignment by Linear Modeling |
ACL
2010
14 years 8 months ago
2010
We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model scores extraction sets: nested ...
60
Voted
ACL
2009
14 years 8 months ago
2009
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
ICASSP
2010
IEEE
14 years 8 months ago
2010
IEEE
We investigate incremental word learning with few training examples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowle...
ICASSP
2010
IEEE
14 years 10 months ago
2010
IEEE
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
101
click to vote
BMCBI
2010
14 years 10 months ago
2010
Background: Accurate classification into genotypes is critical in understanding evolution of divergent viruses. Here we report a new approach, MuLDAS, which classifies a query seq...