71 search results - page 3 / 15 » Improving Statistical Word Alignments with Morpho-syntactic ... |
124
click to vote
IAJIT
2011
14 years 6 months ago
2011
: Multilingual natural language processing systems are increasingly relying on parallel corpus to ameliorate their output. Parallel corpora constitute the basic block for training ...
TASLP
2008
14 years 11 months ago
2008
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....
110
click to vote
ACL
2004
15 years 1 months ago
2004
The parameters of statistical translation models are typically estimated from sentence-aligned parallel corpora. We show that significant improvements in the alignment and transla...
ACL
2007
15 years 1 months ago
2007
We present a general framework to incorporate prior knowledge such as heuristics or linguistic features in statistical generative word alignment models. Prior knowledge plays a ro...
106
click to vote
ACL
2012
13 years 2 months ago
2012
Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...