Skip to Main Content
Table A.1 

Normalized log-likelihood of the EM algorithm for a different number of training epochs and different implementations of the update rule for the translation model, including batch, incremental, and interlaced versions. Results executed on the XRCE and Europarl English–Spanish training corpora are shown.

Norm. Log-likelihood
#EpochsXRCEEuroparl
Batch EM -41.8 -90.9 
Incr. EM -41.8 -91.6 
Incr. EM (Interlaced, R=10) -40.3 -87.1 
Incr. EM (Interlaced, R=100) -40.0 -85.6 
Incr. EM (Interlaced, R=1000) -39.6 -84.5 
Norm. Log-likelihood
#EpochsXRCEEuroparl
Batch EM -41.8 -90.9 
Incr. EM -41.8 -91.6 
Incr. EM (Interlaced, R=10) -40.3 -87.1 
Incr. EM (Interlaced, R=100) -40.0 -85.6 
Incr. EM (Interlaced, R=1000) -39.6 -84.5 
Close Modal

or Create an Account

Close Modal
Close Modal