Hierarchical Reinforcement Learning for Adaptive Text Generation
Hierarchical Reinforcement Learning for Adaptive Text Generation
复制标题
DOI：
--
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Nina Dethlefs;H. Cuayáhuitl
中科院分区：
文献类型：
--
作者：
Nina Dethlefs;H. Cuayáhuitl
我们提出了一种新的自然语言生成(NLG)方法，它将分层强化学习应用到寻路领域的文本生成中。我们的方法旨在优化本质上不同的NLG任务的集成，例如内容选择、文本结构、用户建模、引用表达式生成(REG)和表面实现的决策。它还旨在捕捉这些领域之间现有的相互依存关系。我们应用分层强化学习来学习一种生成策略，该策略捕获这些相互依赖关系，并且可以被转移到其他NLG任务中。我们的实验结果-在模拟环境中-表明，学习的寻路策略比采取合理操作但没有优化的基线策略性能更好。
We present a novel approach to natural language generation (NLG) that applies hierarchical reinforcement learning to text generation in the wayfinding domain. Our approach aims to optimise the integration of NLG tasks that are inherently different in nature, such as decisions of content selection, text structure, user modelling, referring expression generation (REG), and surface realisation. It also aims to capture existing interdependencies between these areas. We apply hierarchical reinforcement learning to learn a generation policy that captures these interdependencies, and that can be transferred to other NLG tasks. Our experimental results---in a simulated environment---show that the learnt wayfinding policy outperforms a baseline policy that takes reasonable actions but without optimization.