@inproceedings{zhou-etal-2022-hierarchical-control,
    title = "Hierarchical Control of Situated Agents through Natural Language",
    author = "Zhou, Shuyan  and
      Yin, Pengcheng  and
      Neubig, Graham",
    editor = "Chen, Wenhu  and
      Chen, Xinyun  and
      Chen, Zhiyu  and
      Yao, Ziyu  and
      Yasunaga, Michihiro  and
      Yu, Tao  and
      Zhang, Rui",
    booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)",
    month = jul,
    year = "2022",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.suki-1.8/",
    doi = "10.18653/v1/2022.suki-1.8",
    pages = "67--84",
    abstract = "When humans perform a particular task, they do so hierarchically: splitting higher-level tasks into smaller sub-tasks. However, most works on natural language (NL) command of situated agents have treated the procedures to be executed as flat sequences of simple actions, or any hierarchies of procedures have been shallow at best. In this paper, we propose a formalism of procedures as programs, a method for representing hierarchical procedural knowledge for agent command and control aimed at enabling easy application to various scenarios. We further propose a modeling paradigm of hierarchical modular networks, which consist of a planner and reactors that convert NL intents to predictions of executable programs and probe the environment for information necessary to complete the program execution. We instantiate this framework on the IQA and ALFRED datasets for NL instruction following. Our model outperforms reactive baselines by a large margin on both datasets. We also demonstrate that our framework is more data-efficient, and that it allows for fast iterative development."
}