关于奖励结构学习Agent的可能性：语言随机集上的互信息
On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets
摘要：
我们提出了第一次尝试阐明一个理论和经验的方法来设计奖励提供的自然语言环境的一些结构学习代理。为此，我们重新审视的信息论的无监督诱导的短语结构语法的行为特征的模拟行动建模为集值随机变量（随机集的语言样本）构成语义结构。我们的研究结果表明，模拟的语义结构（开放信息抽取三元组）可以区分随机构建的观察其成分之间的互信息的经验证据。这表明了奖励结构学习代理的可能性，而不使用预先训练的结构分析器（Oracle演员/专家）。
英文摘要：
We present a first attempt to elucidate a theoretical and empirical approach to design the reward provided by a natural language environment to some structure learning agent. To this end, we revisit the Information Theory of unsupervised induction of phrase-structure grammars to characterize the behavior of simulated actions modeled as set-valued random variables (random sets of linguistic samples) constituting semantic structures. Our results showed empirical evidence of that simulated semantic structures (Open Information Extraction triplets) can be distinguished from randomly constructed ones by observing the Mutual Information among their constituents. This suggests the possibility of rewarding structure learning agents without using pretrained structural analyzers (oracle actors/experts).
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。
