Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations

TL;DR

This paper introduces Chirpy Cardinal, an open-domain socialbot that uses neural generation to create emotionally engaging, personalized conversations with real users, achieving competitive ratings and long interaction durations.

Contribution

It presents a novel socialbot platform that combines neural generation with emotional and personalized dialogue capabilities for open-domain conversations.

Findings

Achieved an average user rating of 3.6/5.0

Median conversation duration of 2 minutes 16 seconds

Over 12 minutes for 90th percentile conversations

Abstract

We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging - such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms - prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, personalized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our conversational and emotional tone. At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3.6/5.0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.