Intent Generation for Goal-Oriented Dialogue Systems based on Schema.org Annotations
This addresses scalability issues for open dialogue systems working with diverse data and APIs, though it is incremental as it builds on existing semantic web annotations.
The paper tackles the problem of manual intent creation in goal-oriented dialogue systems by introducing a method to automatically generate intents and slots from schema.org annotations, enabling adaptation to new APIs without heavy developer involvement.
Goal-oriented dialogue systems typically communicate with a backend (e.g. database, Web API) to complete certain tasks to reach a goal. The intents that a dialogue system can recognize are mostly included to the system by the developer statically. For an open dialogue system that can work on more than a small set of well curated data and APIs, this manual intent creation will not scalable. In this paper, we introduce a straightforward methodology for intent creation based on semantic annotation of data and services on the web. With this method, the Natural Language Understanding (NLU) module of a goal-oriented dialogue system can adapt to newly introduced APIs without requiring heavy developer involvement. We were able to extract intents and necessary slots to be filled from schema.org annotations. We were also able to create a set of initial training sentences for classifying user utterances into the generated intents. We demonstrate our approach on the NLU module of a state-of-the art dialogue system development framework.