CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication

Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, Devi Parikh


Abstract
In this work, we propose a goal-driven collaborative task that combines language, perception, and action. Specifically, we develop a Collaborative image-Drawing game between two agents, called CoDraw. Our game is grounded in a virtual world that contains movable clip art objects. The game involves two players: a Teller and a Drawer. The Teller sees an abstract scene containing multiple clip art pieces in a semantically meaningful configuration, while the Drawer tries to reconstruct the scene on an empty canvas using available clip art pieces. The two players communicate with each other using natural language. We collect the CoDraw dataset of ~10K dialogs consisting of ~138K messages exchanged between human players. We define protocols and metrics to evaluate learned agents in this testbed, highlighting the need for a novel “crosstalk” evaluation condition which pairs agents trained independently on disjoint subsets of the training data. We present models for our task and benchmark them using both fully automated evaluation and by having them play the game live with humans.
Anthology ID:
P19-1651
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6495–6513
Language:
URL:
https://aclanthology.org/P19-1651
DOI:
10.18653/v1/P19-1651
Bibkey:
Cite (ACL):
Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, and Devi Parikh. 2019. CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6495–6513, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication (Kim et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/P19-1651.pdf
Code
 facebookresearch/CoDraw +  additional community code
Data
CoDraw