Towards Personalized Dialog Policies for Conversational Skill Discovery
This addresses skill discovery for businesses and consumers using voice services, but it is incremental as it builds on existing rule-based methods with reinforcement learning.
The paper tackles the problem of discovering custom voice skills for users by developing a conversational agent that uses reinforcement learning to adapt to user attributes and conversational styles, showing effectiveness in a real production setting.
Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills). As the number of these experiences increases, a key problem is the discovery of skills that can be used to address a user's request. In this paper, we focus on conversational skill discovery and present a conversational agent which engages in a dialog with users to help them find the skills that fulfill their needs. To this end, we start with a rule-based agent and improve it by using reinforcement learning. In this way, we enable the agent to adapt to different user attributes and conversational styles as it interacts with users. We evaluate our approach in a real production setting by deploying the agent to interact with real users, and show the effectiveness of the conversational agent in helping users find the skills that serve their request.