Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation
This work addresses the problem of evaluating instruction fidelity in VLN for AI researchers, though it is incremental as it builds on existing datasets and metrics.
The authors identified shortcomings in existing metrics for Vision-and-Language Navigation (VLN), particularly the Room-to-Room dataset's focus on goal completion over instruction fidelity, and proposed a new metric, Coverage weighted by Length Score (CLS), and a new dataset, Room-for-Room (R4R), showing that agents rewarded for instruction fidelity outperform those focused on goal completion.
Advances in learning and representations have reinvigorated work that connects language to other modalities. A particularly exciting direction is Vision-and-Language Navigation(VLN), in which agents interpret natural language instructions and visual scenes to move through environments and reach goals. Despite recent progress, current research leaves unclear how much of a role language understanding plays in this task, especially because dominant evaluation metrics have focused on goal completion rather than the sequence of actions corresponding to the instructions. Here, we highlight shortcomings of current metrics for the Room-to-Room dataset (Anderson et al.,2018b) and propose a new metric, Coverage weighted by Length Score (CLS). We also show that the existing paths in the dataset are not ideal for evaluating instruction following because they are direct-to-goal shortest paths. We join existing short paths to form more challenging extended paths to create a new data set, Room-for-Room (R4R). Using R4R and CLS, we show that agents that receive rewards for instruction fidelity outperform agents that focus on goal completion.