Towards Personalized Dialog Policies for Conversational Skill Discovery

Abstract

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.

arXiv commentThe 3rd Conversational AI workshop - today's practice and tomorrow's potential

References in corpus (10)

• Playing Atari with Deep Reinforcement Learning
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• A User Simulator for Task-Completion Dialogues
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
• Attentive Memory Networks: Efficient Machine Reading for Conversational Search
• Learning Robust Dialog Policies in Noisy Environments
• SimpleDS: A Simple Deep Reinforcement Learning Dialogue System
• The Technological Gap Between Virtual Assistants and Recommendation Systems
• Efficient Large-Scale Domain Classification with Personalized Attention