The Emergence of High-Level Semantics in a Signaling Game

Timothée Bernard, Timothee Mickus, Hiroya Takamura


Abstract
The symbol grounding problem—how to connect a symbolic system to the outer world—is a longstanding question in AI that has recently gained prominence with the progress made in NLP in general and surrounding large language models in particular. In this article, we study the emergence of semantic categories in the communication protocol developed by neural agents involved in a well-established type of signaling game. In its basic form, the game requires one agent to retrieve an image based on a message produced by a second agent. We first show that the agents are able to, and do, learn to communicate high-level semantic concepts rather than low-level features of the images even from very indirect training signal to that end. Second, we demonstrate that the introduction of an adversarial agent in the game fosters the emergence of semantics by producing an appropriate training signal when no other method is available.
Anthology ID:
2024.starsem-1.16
Volume:
Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Danushka Bollegala, Vered Shwartz
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
200–211
Language:
URL:
https://aclanthology.org/2024.starsem-1.16
DOI:
10.18653/v1/2024.starsem-1.16
Bibkey:
Cite (ACL):
Timothée Bernard, Timothee Mickus, and Hiroya Takamura. 2024. The Emergence of High-Level Semantics in a Signaling Game. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 200–211, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
The Emergence of High-Level Semantics in a Signaling Game (Bernard et al., *SEM 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.starsem-1.16.pdf