Learning Interpretable Spatial Operations in a Rich 3D Blocks World
This work addresses the challenge of interpreting complex spatial language for AI systems, but it is incremental as it builds on existing simulation environments and datasets.
The paper tackles the problem of mapping natural language instructions to complex spatial actions in a 3D blocks world by introducing a new dataset with richer language and more configurations, and proposes a neural architecture that achieves competitive results while discovering interpretable spatial operations.
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)