Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models

05/24/2022
by   Tadahiro Taniguchi, et al.
0

Emergent communication, also known as symbol emergence, seeks to investigate computational models that can better explain human language evolution and the creation of symbol systems. This study aims to provide a new model for emergent communication, which is based on a probabilistic generative model. We define the Metropolis-Hastings (MH) naming game by generalizing a model proposed by Hagiwara et al. <cit.>. The MH naming game is a sort of MH algorithm for an integrative probabilistic generative model that combines two agents playing the naming game. From this viewpoint, symbol emergence is regarded as decentralized Bayesian inference, and semiotic communication is regarded as inter-personal cross-modal inference. We also offer Inter-GMM+VAE, a deep generative model for simulating emergent communication, in which two agents create internal representations and categories and share signs (i.e., names of objects) from raw visual images observed from different viewpoints. The model has been validated on MNIST and Fruits 360 datasets. Experiment findings show that categories are formed from real images observed by agents, and signs are correctly shared across agents by successfully utilizing both of the agents' views via the MH naming game. Furthermore, it has been verified that the visual images were recalled from the signs uttered by the agents. Notably, emergent communication without supervision and reward feedback improved the performance of unsupervised representation learning.

READ FULL TEXT

page 6

page 7

research
05/31/2019

Symbol Emergence as an Interpersonal Multimodal Categorization

This study focuses on category formation for individual agents and the d...
research
05/31/2023

Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models

In the studies on symbol emergence and emergent communication in a popul...
research
05/31/2023

Metropolis-Hastings algorithm in joint-attention naming game: Experimental semiotics study

In this study, we explore the emergence of symbols during interactions b...
research
05/24/2022

Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word

In this study, we propose a head-to-head type (H2H-type) inter-personal ...
research
08/31/2018

How agents see things: On visual representations in an emergent language game

There is growing interest in the language developed by agents interactin...
research
09/15/2021

Multiagent Multimodal Categorization for Symbol Emergence: Emergent Communication via Interpersonal Cross-modal Inference

This paper describes a computational model of multiagent multimodal cate...
research
06/27/2023

Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality

We present a computational model for a symbol emergence system that enab...

Please sign up or login with your details

Forgot password? Click here to reset