Human intelligence can remarkably adapt quickly to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research which can enable similar capabilities in machines, we made the following contributions (1) formalized the collaborative embodied agent using natural language task; (2) developed a tool for extensive and scalable data collection; and (3) collected the first dataset for interactive grounded language understanding.
@article{arxiv.2211.06552,
title = {Collecting Interactive Multi-modal Datasets for Grounded Language Understanding},
author = {Shrestha Mohanty and Negar Arabzadeh and Milagro Teruel and Yuxuan Sun and Artem Zholus and Alexey Skrynnik and Mikhail Burtsev and Kavya Srinet and Aleksandr Panov and Arthur Szlam and Marc-Alexandre Côté and Julia Kiseleva},
journal= {arXiv preprint arXiv:2211.06552},
year = {2023}
}