A new dataset and model for learning to understand navigational instructions
This work addresses the challenge of grounded language learning for navigation, but it is incremental as it builds on the existing SAIL dataset with improvements.
The paper tackles the problem of learning to follow navigational instructions by introducing a new model that achieves state-of-the-art results on the SAIL dataset and a synthetic dataset generator, SAILx, to address dataset size and balance issues.
In this paper, we present a state-of-the-art model and introduce a new dataset for grounded language learning. Our goal is to develop a model that can learn to follow new instructions given prior instruction-perception-action examples. We based our work on the SAIL dataset which consists of navigational instructions and actions in a maze-like environment. The new model we propose achieves the best results to date on the SAIL dataset by using an improved perceptual component that can represent relative positions of objects. We also analyze the problems with the SAIL dataset regarding its size and balance. We argue that performance on a small, fixed-size dataset is no longer a good measure to differentiate state-of-the-art models. We introduce SAILx, a synthetic dataset generator, and perform experiments where the size and balance of the dataset are controlled.