Improving NLU Training over Linked Data with Placeholder Concepts

摘要

Conversational systems, also known as dialogue systems, have become increasingly popular. They can perform a variety of tasks e.g. in B2C areas such as sales and customer services. A significant amount of research has already been conducted on improving the underlying algorithms of the natural language understanding (NLU) component of dialogue systems. This paper presents an approach to generate training datasets for the NLU component from Linked Data resources. We analyze how differently designed training datasets can impact the performance of the NLU component. Whereby, the training datasets differ mainly by varying values for the injection into fixed sentence patterns. As a core contribution, we introduce and evaluate the performance of different placeholder concepts. Our results show that a trained model with placeholder concepts is capable of handling dynamic Linked Data without retraining the NLU component. Thus, our approach also contributes to the robustness of the NLU component.