Multi-dynamic Bayesian Networks

We present a generalization of dynamic Bayesian networks to concisely describe complex probability distributions such as in problems with multiple interacting variable-length streams of random variables. Our framework incorporates recent graphical model constructs to account for existence uncert ainty, value-specific independence, aggregation relationships, and local and gl obal constraints, while still retaining a Bayesian network interpretation and effic ient inference and learn- ing techniques. We introduce one such general technique, which is an extension of Value Elimination, a backtracking search inference algorithm. Multi-dynamic Bayesian networks are motivated by our work on Statistical Machine Transla- tion (MT). We present results on MT word alignment in support of our claim that MDBNs are a promising framework for the rapid prototyping of new MT systems.