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

Published in 3rd Proceedings of Alexa Prize (Alexa Prize 2019)

References in corpus (5)

• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Alquist 2.0: Alexa Prize Socialbot Based on Sub-Dialogue Models
• Gunrock: A Social Bot for Complex and Engaging Long Conversations
• Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Cited by in corpus (5)

• Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
• Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization
• CASPR: A Commonsense Reasoning-based Conversational Socialbot
• Proto: A Neural Cocktail for Generating Appealing Conversations
• Medical Literature Mining and Retrieval in a Conversational Setting