Sciweavers

TASLP
2008
142views more  TASLP 2008»
13 years 3 months ago
HMM Word and Phrase Alignment for Statistical Machine Translation
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently....
Yonggang Deng, William J. Byrne
ICPR
2008
IEEE
13 years 10 months ago
Embedding HMM's-based models in a Euclidean space: The topological hidden Markov models
One of the major limitations of HMM-based models is the inability to cope with topology: When applied to a visible observation (VO) sequence, HMM-based techniques have difficulty ...
Djamel Bouchaffra