On the role of population heterogeneity in emergent communication - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

On the role of population heterogeneity in emergent communication

Résumé

Populations have often been perceived as a structuring component for language to emerge and evolve: the larger the population, the more structured the language. While this observation is widespread in the sociolinguistic literature, it has not been consistently reproduced in computer simulations with neural agents. In this paper, we thus aim to clarify this apparent contradiction. We explore emergent language properties by varying agent population size in the speaker-listener Lewis Game. After reproducing the experimental difference, we challenge the simulation assumption that the agent community is homogeneous. We then investigate how speaker-listener asymmetry alters language structure through the analysis a potential diversity factor: learning speed. From then, we leverage this observation to control population heterogeneity without introducing confounding factors. We finally show that introducing such training speed heterogeneities naturally sort out the initial contradiction: larger simulated communities start developing more stable and structured languages.
Fichier principal
Vignette du fichier
2204.12982.pdf (681.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03830500 , version 1 (26-10-2022)

Identifiants

  • HAL Id : hal-03830500 , version 1

Citer

Mathieu Rita, Florian Strub, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux. On the role of population heterogeneity in emergent communication. ICLP 2022 - Tenth International Conference on Learning Representations, Apr 2022, Los Angeles, United States. ⟨hal-03830500⟩
71 Consultations
21 Téléchargements

Partager

Gmail Facebook X LinkedIn More