Contrastive Estimation: Training Log-Linear Models on ...

Contrastive Estimation: (Efficiently) Training Log-Linear Models (of Sequences) on Unlabeled Data Noah A. Smith and Jason Eisner Department of Computer Science / Center for Language and Speech Processing Johns Hopkins University {nasmith,jason}@cs.jhu.edu Nutshell Version Maximum Likelihood Estimation (Supervised) Maximum Likelihood...

Author:
Uploaded by: Murkka Svensdottir
Filesize: 2 MB