CB2: Collaborative Natural Language Interaction Research Platform

Jacob Sharf, Mustafa Omer Gul, Yoav Artzi


Abstract
CB2 is a multi-agent platform to study collaborative natural language interaction in a grounded task-oriented scenario. It includes a 3D game environment, a backend server designed to serve trained models to human agents, and various tools and processes to enable scalable studies. We deploy CB2 at https://cb2.ai as a system demonstration with a learned instruction following model.
Anthology ID:
2023.acl-demo.39
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Danushka Bollegala, Ruihong Huang, Alan Ritter
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
412–420
Language:
URL:
https://aclanthology.org/2023.acl-demo.39
DOI:
10.18653/v1/2023.acl-demo.39
Bibkey:
Cite (ACL):
Jacob Sharf, Mustafa Omer Gul, and Yoav Artzi. 2023. CB2: Collaborative Natural Language Interaction Research Platform. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 412–420, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
CB2: Collaborative Natural Language Interaction Research Platform (Sharf et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-demo.39.pdf
Video:
 https://aclanthology.org/2023.acl-demo.39.mp4