A Systematic Survey of Text Worlds as Embodied Natural Language Environments
A Systematic Survey of Text Worlds as Embodied Natural Language Environments
复制标题
DOI：
10.18653/v1/2022.wordplay-1.1
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Peter Alexander Jansen
中科院分区：
文献类型：
--
作者：
Peter Alexander Jansen
文本世界是实体代理的虚拟环境，与 2D 或 3D 环境不同，它专门使用文本描述来呈现。这些环境因其较低的进入门槛而提供了高保真 3D 环境的替代方案，提供了研究语义、组合推理和其他具有丰富动作空间的高级任务的能力，同时控制感知输入。这项系统调查概述了文本世界工具、环境和代理建模的最新发展，同时研究了知识图谱、常识推理、将文本世界性能迁移学习到更高保真度环境的最新趋势，以及近期发展目标，一旦实现，将使文本世界成为自然语言处理领域有吸引力的通用研究范式。
Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry, providing the ability to study semantics, compositional inference, and other high-level tasks with rich action spaces while controlling for perceptual input. This systematic survey outlines recent developments in tooling, environments, and agent modeling for Text Worlds, while examining recent trends in knowledge graphs, common sense reasoning, transfer learning of Text World performance to higher-fidelity environments, as well as near-term development targets that, once achieved, make Text Worlds an attractive general research paradigm for natural language processing.