Integrating a Dialog Component into a Framework for Spoken Language Understanding

We develop PARSE, a framework for deep spoken language understanding. We use it for naturalistic end-user programming in spoken natural language. In this paper, we extend PARSE with a reactive dialog component to elicit additional user input and resolve natural language understanding issues. Dialog systems have been well studied but most applications are designed for dialog from the ground up - we see dialog primarily as a means to an end. Therefore, we integrated a dialog component with PARSE without affecting its other components: We modularize the dialog management and introduce Dialog Acts that bundle a trigger for the dialog and the reaction of the system. We implemented three Dialog Acts to address the following issues: speech recognition uncertainties, coreference ambiguities, and incomplete conditionals.We conducted a user study with ten subjects to evaluate our approach. The dialog component achieved resolution rates of 23% up to 50% (depending on the Dialog Act) and introduces a negligible number of errors. We expect the overall performance to increase even further with the implementation of additional Dialog Acts.