Learning Interpretable Spatial Operations in a Rich 3D Blocks World

Learning Interpretable Spatial Operations in a Rich 3D Blocks World
复制标题

在丰富的 3D 块世界中学习可解释的空间操作

DOI:
10.1609/aaai.v32i1.12026
复制
发表时间:
2017
期刊:
ArXiv
影响因子:
--
通讯作者:
D. Marcu
D. Marcu
中科院分区:
--
文献类型:
--
作者:
Yonatan Bisk;Kevin J. Shih;Yejin Choi;D. Marcu

文献摘要

参考文献

被引文献

相似文献

在本文中,我们研究了在3D障碍世界中绘制自然语言指示的问题,我们首先引入了一个新的数据集,将复杂的3D空间操作与丰富的自然语言描述配对,需要复杂的空间和务实的解释,例如“镜像”,“扭曲”和“平衡”。在2D环境中,具有100个新世界配置和250,000个令牌的原始数据集的大小,同时提出了一个新的神经体系结构,同时可以自动发现可解释的空间操作的清单,同时又提出了更加复杂的,同时还增加了一倍(图5)。
In this paper, we study the problem of mapping natural language instructions to complex spatial actions in a 3D blocks world. We first introduce a new dataset that pairs complex 3D spatial operations to rich natural language descriptions that require complex spatial and pragmatic interpretations such as “mirroring”, “twisting”, and “balancing”. This dataset, built on the simulation environment of Bisk, Yuret, and Marcu (2016), attains language that is significantly richer and more complex, while also doubling the size of the original dataset in the 2D environment with 100 new world configurations and 250,000 tokens. In addition, we propose a new neural architecture that achieves competitive results while automatically discovering an inventory of interpretable spatial operations (Figure 5).
DOI: --
发表时间: 2017-10
期刊: --
影响因子: --
作者:
Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney
通讯作者: Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney