A Simple, Fast, and Effective Reparameterization of IBM Model 2

Chris Dyer, Victor Chahuneau and Noah A. Smith

We present a simple log-linear reparameterization of IBM Model 2 that overcomes problems arising from Model 1's strong assumptions and Model 2's overparameterization. Efficient inference, likelihood evaluation, and parameter estimation algorithms are provided. Training the model is consistently ten times faster than Model 4. On three large-scale translation tasks, systems built using our alignment model outperform IBM Model 4.

Back to Papers Accepted