Ruuh: A Deep Learning Based Conversational Social Agent
This work tackles the challenge of building intelligent conversational agents that go beyond utilitarian responses to meet social and emotional needs for real-world users, though it appears incremental in applying deep learning to social interaction.
The paper presents Ruuh, a deep learning-based conversational social agent designed by Microsoft India to engage users on diverse topics and address social needs like empathy and handling abusive language. The agent has interacted with over 2 million users, generating more than 150 million conversations.
Dialogue systems and conversational agents are becoming increasingly popular in the modern society but building an agent capable of holding intelligent conversation with its users is a challenging problem for artificial intelligence. In this demo, we demonstrate a deep learning based conversational social agent called "Ruuh" (facebook.com/Ruuh) designed by a team at Microsoft India to converse on a wide range of topics. Ruuh needs to think beyond the utilitarian notion of merely generating "relevant" responses and meet a wider range of user social needs, like expressing happiness when user's favorite team wins, sharing a cute comment on showing the pictures of the user's pet and so on. The agent also needs to detect and respond to abusive language, sensitive topics and trolling behavior of the users. Many of these problems pose significant research challenges which will be demonstrated in our demo. Our agent has interacted with over 2 million real world users till date which has generated over 150 million user conversations.