Towards the Rapid Development of a Natural Language Understanding Module
This addresses the need for efficient prototyping in conversational AI development, though it appears incremental as it applies existing learning paradigms to specific use cases.
The paper tackles the problem of rapidly developing a natural language understanding module for conversational agents, enabling non-experts to create prototypes quickly, and demonstrates its application in art and cinema domains with practical testing.
When developing a conversational agent, there is often an urgent need to have a prototype available in order to test the application with real users. A Wizard of Oz is a possibility, but sometimes the agent should be simply deployed in the environment where it will be used. Here, the agent should be able to capture as many interactions as possible and to understand how people react to failure. In this paper, we focus on the rapid development of a natural language understanding module by non experts. Our approach follows the learning paradigm and sees the process of understanding natural language as a classification problem. We test our module with a conversational agent that answers questions in the art domain. Moreover, we show how our approach can be used by a natural language interface to a cinema database.