Emergence of Hierarchical Reference Systems in Multi-agent Communication

Xenia Ohmer, Marko Duda, Elia Bruni


Abstract
In natural language, referencing objects at different levels of specificity is a fundamental pragmatic mechanism for efficient communication in context. We develop a novel communication game, the hierarchical reference game, to study the emergence of such reference systems in artificial agents. We consider a simplified world, in which concepts are abstractions over a set of primitive attributes (e.g., color, style, shape). Depending on how many attributes are combined, concepts are more general (“circle”) or more specific (“red dotted circle”). Based on the context, the agents have to communicate at different levels of this hierarchy. Our results show that the agents learn to play the game successfully and can even generalize to novel concepts. To achieve abstraction, they use implicit (omitting irrelevant information) and explicit (indicating that attributes are irrelevant) strategies. In addition, the compositional structure underlying the concept hierarchy is reflected in the emergent protocols, indicating that the need to develop hierarchical reference systems supports the emergence of compositionality.
Anthology ID:
2022.coling-1.501
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5689–5706
Language:
URL:
https://aclanthology.org/2022.coling-1.501
DOI:
Bibkey:
Cite (ACL):
Xenia Ohmer, Marko Duda, and Elia Bruni. 2022. Emergence of Hierarchical Reference Systems in Multi-agent Communication. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5689–5706, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Emergence of Hierarchical Reference Systems in Multi-agent Communication (Ohmer et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.501.pdf
Code
 xeniaohmer/hierarchical_reference_game