Gated-Attention Architectures for Task-Oriented Language Grounding
This addresses the problem of enabling autonomous agents to interpret and execute language instructions in complex 3D settings, representing an incremental advancement in language grounding methods.
The paper tackles task-oriented language grounding by proposing an end-to-end neural architecture that uses a Gated-Attention mechanism to map natural language instructions to actions in 3D environments, achieving effectiveness on unseen instructions and maps with quantitative and qualitative results.
To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called task-oriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. The proposed model combines the image and text representations using a Gated-Attention mechanism and learns a policy to execute the natural language instruction using standard reinforcement and imitation learning methods. We show the effectiveness of the proposed model on unseen instructions as well as unseen maps, both quantitatively and qualitatively. We also introduce a novel environment based on a 3D game engine to simulate the challenges of task-oriented language grounding over a rich set of instructions and environment states.