The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations

Daniel Akkerman, Phong Le, Raquel G. Alhama


Abstract
To study the requirements needed for a human-like language to develop, Language Emergence research uses jointly trained artificial agents which communicate to solve a task, the most popular of which is a referential game. The targets that agents refer to typically involve a single entity, which limits their ecological validity and the complexity of the emergent languages. Here, we present a simple multi-entity game in which targets include multiple entities that are spatially related. We ask whether agents dealing with multi-entity targets benefit from the use of graph representations, and explore four different graph schemes. Our game requires more sophisticated analyses to capture the extent to which the emergent languages are compositional, and crucially, what the decomposed features are. We find that emergent languages from our setup exhibit a considerable degree of compositionality, but not over all features.
Anthology ID:
2024.emnlp-main.1042
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18713–18723
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1042/
DOI:
10.18653/v1/2024.emnlp-main.1042
Bibkey:
Cite (ACL):
Daniel Akkerman, Phong Le, and Raquel G. Alhama. 2024. The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18713–18723, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations (Akkerman et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1042.pdf
Software:
 2024.emnlp-main.1042.software.zip
Data:
 2024.emnlp-main.1042.data.zip