Customer care dialog management, an inverse reinforcement learning approach

Abstract

In the last decade we’ve seen advances in speech recognition, natural language understanding, natural language generation, and speech synthesis to such an extent that conversational interfaces are becoming possible. Indeed, personal assistants like Apple Siri, Microsoft Cortana, and Nuance DMA have brought conversational agents into popular use. In addition, task-based agents have begun to partially automate activities like hotel reservations and limited banking functions.

However, rich and demanding tasks such as those needed to automate customer care environments especially those performing troubleshooting require significant progress to become viable. Many dialog systems are still based on deterministic approaches with a pre-defined set of tasks where adaptability is limited.