论文标题
神经产生遇到真实的人：建立一个社交，内容丰富的开放域对话代理商
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
论文作者
论文摘要
我们提出了一个开放域的社交聊天机器人Chirpy Cardinal。为了既有信息又有信息，我们的机器人以真实的，情感上的方式与用户聊天。通过将受控的神经产生与脚手架，手写的对话整合在一起，我们让用户和机器人轮流推动对话，从而产生一种吸引人且具有社交流利的体验。 Chirpy Cardinal部署在Alexa奖Socialbot Grand Challenge的第四次迭代中，每天处理数千次对话，在9个机器人中排名第二，平均用户评级为3.58/5。
We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way. By integrating controlled neural generation with scaffolded, hand-written dialogue, we let both the user and bot take turns driving the conversation, producing an engaging and socially fluent experience. Deployed in the fourth iteration of the Alexa Prize Socialbot Grand Challenge, Chirpy Cardinal handled thousands of conversations per day, placing second out of nine bots with an average user rating of 3.58/5.
