No abstract

Sitting at the intersection between statistics and machine learning, Dynamic Bayesian Networks have been applied with much success in many domains, such as speech recognition, vision, and computational biology. While Natural Language Processing increasingly relies on statistical methods, we think they have yet to use Graphical Models to their full potential. In this paper, we report on experiments in learning edit distance costs using Dynamic Bayesian Networks and present results on a pronunciation classification task. By exploiting the ability within the DBN framework to rapidly explore a large model space, we obtain a 40% reduction in error rate compared to a previous transducer-based method of learning edit distance.

We present a new multilingual statistical MT word alignment model based on a simple extension of the IBM and HMM Models and a two-step alignment procedure. Preliminary results on a small hand-aligned subset of the Europarl corpus show a 7% relative improvement over a state of the art alignment model.

No abstract

No abstract