arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.10387cs.HCcs.AI
收藏

可教的会话主体

Towards Teachable Conversational Agents

University of Waterloo(滑铁卢大学)

Nalin Chhibber, Edith Law

摘要:

构建交互式机器学习系统的传统过程可以被视为教师-学习者交互场景,其中机器学习者由一个或多个人类教师训练。在这项工作中,我们探讨了使用对话界面来研究人类教师和交互式机器学习者之间的交互的想法。具体来说,我们研究了可教学人工智能智能体是否可以通过对话交互从人类教师那里可靠地学习,以及这种学习与传统的监督学习算法相比如何。结果验证了可教会话代理的概念,并强调了相关的因素,旨在从会话交互学习的机器学习系统的发展。

英文摘要:

The traditional process of building interactive machine learning systems can be viewed as a teacher-learner interaction scenario where the machine-learners are trained by one or more human-teachers. In this work, we explore the idea of using a conversational interface to investigate the interaction between human-teachers and interactive machine-learners. Specifically, we examine whether teachable AI agents can reliably learn from human-teachers through conversational interactions, and how this learning compare with traditional supervised learning algorithms. Results validate the concept of teachable conversational agents and highlight the factors relevant for the development of machine learning systems that intend to learn from conversational interactions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑