LittleMu：通过异构资源整合与“教学链”提示部署在线虚拟助教
LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain of Teach Prompts
AI总结：
本文提出虚拟MOOC助教LittleMu，通过异构知识源检索与“教学链”提示利用预训练模型，以极少标注数据实现问答和闲聊，并在学堂在线平台服务超8万用户。
摘要：
助教在漫长的教育历史中一直扮演着重要角色。然而，由于现实世界在线教育场景的复杂性以及训练数据的缺乏，很少有MOOC平台能够提供人工或虚拟助教来支持大规模在线学生的学习。在本文中，我们提出了一个虚拟MOOC助教系统LittleMu，该系统仅需极少量有标注的训练数据，即可提供问答和闲聊服务。LittleMu由异构检索和语言模型提示两个交互模块组成，首先整合结构化、半结构化和非结构化知识源，以支持对广泛问题的准确回答。然后，我们设计了名为“教学链（Chain of Teach）”的精细示范提示，以利用大规模预训练模型来处理复杂的未收录问题。除问答外，我们还开发了其他教育服务，如基于知识的闲聊。我们通过离线评估和在线部署两种方式测试了系统性能。自2020年5月以来，我们的LittleMu系统已在学堂在线MOOC平台上服务超过80,000名用户，处理来自500多门课程的超过300,000条查询，持续为更便捷、更公平的教育做出贡献。我们的代码、服务和数据集将在https://github.com/THU-KEG/VTA上公开。
英文摘要：
Teaching assistants have played essential roles in the long history of education. However, few MOOC platforms are providing human or virtual teaching assistants to support learning for massive online students due to the complexity of real-world online education scenarios and the lack of training data. In this paper, we present a virtual MOOC teaching assistant, LittleMu with minimum labeled training data, to provide question answering and chit-chat services. Consisting of two interactive modules of heterogeneous retrieval and language model prompting, LittleMu first integrates structural, semi- and unstructured knowledge sources to support accurate answers for a wide range of questions. Then, we design delicate demonstrations named "Chain of Teach" prompts to exploit the large-scale pre-trained model to handle complex uncollected questions. Except for question answering, we develop other educational services such as knowledge-grounded chit-chat. We test the system's performance via both offline evaluation and online deployment. Since May 2020, our LittleMu system has served over 80,000 users with over 300,000 queries from over 500 courses on XuetangX MOOC platform, which continuously contributes to a more convenient and fair education. Our code, services, and dataset will be available at https://github.com/THU-KEG/VTA.
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。
