arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.08554cs.AI
收藏

学习提问:通过20个问题获得知识获取

Learning-to-Ask: Knowledge Acquisition via 20 Questions

Tsinghua University(清华大学);Microsoft Research(微软研究院);Alibaba AI Labs(阿里巴巴人工智能实验室)

Yihong Chen, Bei Chen, Xuguang Duan, Jian-Guang Lou, Yue Wang, Wenwu Zhu, Yong Cao

摘要:

几乎所有的知识授权应用程序都依赖于准确的知识,这些知识要么必须以高成本手动收集,要么必须自动提取,错误无法消除。在本文中,我们研究了20个问题,一个在线互动游戏,其中每个问题-答案对对应于目标实体的一个事实,以获得高准确性的知识,有效地接近零的劳动力成本。通过20个问题的知识获取主要对与人类玩家玩游戏的智能代理提出了两个挑战。第一个是寻找足够的信息,用尽可能少的问题来识别目标实体,第二个是利用剩余的提问机会来有效地获取有价值的知识,这两个都依赖于良好的提问策略。为了应对这些挑战,我们提出了学习提问(LA)框架,在该框架内,智能体分别通过深度强化学习和广义矩阵分解学习智能提问策略,用于信息搜索和知识获取。此外,贝叶斯方法来表示知识,以确保噪声用户响应的鲁棒性。在真实数据上的仿真实验表明,该算法能够为Agent提供有效的提问策略,从而提高了Agent的成功率和知识获取的速度。此外,信息寻求和知识获取的提问策略提高了彼此的性能,允许代理从相对较小的知识集开始,并在没有持续的人类监督的情况下快速提高其知识库。

英文摘要:

Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors. In this paper, we study 20 Questions, an online interactive game where each question-response pair corresponds to a fact of the target entity, to acquire highly accurate knowledge effectively with nearly zero labor cost. Knowledge acquisition via 20 Questions predominantly presents two challenges to the intelligent agent playing games with human players. The first one is to seek enough information and identify the target entity with as few questions as possible, while the second one is to leverage the remaining questioning opportunities to acquire valuable knowledge effectively, both of which count on good questioning strategies. To address these challenges, we propose the Learning-to-Ask (LA) framework, within which the agent learns smart questioning strategies for information seeking and knowledge acquisition by means of deep reinforcement learning and generalized matrix factorization respectively. In addition, a Bayesian approach to represent knowledge is adopted to ensure robustness to noisy user responses. Simulating experiments on real data show that LA is able to equip the agent with effective questioning strategies, which result in high winning rates and rapid knowledge acquisition. Moreover, the questioning strategies for information seeking and knowledge acquisition boost the performance of each other, allowing the agent to start with a relatively small knowledge set and quickly improve its knowledge base in the absence of constant human supervision.

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。

↑