Executing Instructions in Situated Collaborative Interactions
arXiv:1910.03655
Abstract
We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some tasks themselves, and requires the system to effectively recover from errors as the user strategically assigns it new goals. We build a game environment to study this scenario, and learn to map user instructions to system actions. We introduce a learning approach focused on recovery from cascading errors between instructions, and modeling methods to explicitly reason about instructions with multiple goals. We evaluate with a new evaluation protocol using recorded interactions and online games with human users, and observe how users adapt to the system abilities.
arXiv commentEMNLP 2019 long paper
References in corpus (4)
- Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
- Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
- Hierarchical Decision Making by Generating and Following Natural Language Instructions
- MeetUp! A Corpus of Joint Activity Dialogues in a Visual Environment