Applying POMDPs to Dialog Systems in the Troubleshooting Domain

This paper reports on progress applying partially observable Markov decision processes (POMDPs) to a commercial dialog domain: troubleshooting. In the troubleshooting domain, a spoken dialog system helps a user to fix a product such as a failed DSL connection. Past work has argued that a POMDP is a principled approach to building spoken dialog systems in the simpler slot-filling domain; this paper explains how the POMDPs formulation can be extended to the more complex troubleshooting domain. Results from dialog simulation verify that a POMDP outperforms a handcrafted baseline.