Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue
This addresses challenges in training and evaluation for embodied dialogue agents, suggesting a shift to higher-level semantic goals to improve progress in the field.
The paper argues that imitation learning and low-level metrics are misleading for embodied dialogue instruction following, showing that models trained with IL take spurious actions and fail to ground query utterances, which hinders task completion.
Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. The recent introduction of benchmarks (Padmakumar et al., 2022) raises the question of how best to train and evaluate models for this multi-turn, multi-agent, long-horizon task. This paper contributes to that conversation, by arguing that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research and may hinder progress. We provide empirical comparisons of metrics, analysis of three models, and make suggestions for how the field might best progress. First, we observe that models trained with IL take spurious actions during evaluation. Second, we find that existing models fail to ground query utterances, which are essential for task completion. Third, we argue evaluation should focus on higher-level semantic goals.