A Review of the Applications of Deep Learning-Based Emergent Communication
B Boldt, D Mortensen - arXiv preprint arXiv:2407.03302, 2024 - arxiv.org
Emergent communication, or emergent language, is the field of research which studies how
human language-like communication systems emerge de novo in deep multi-agent …
human language-like communication systems emerge de novo in deep multi-agent …
Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game
NL Hoang, T Taniguchi, Y Hagiwara… - Frontiers in Robotics …, 2024 - frontiersin.org
Deep generative models (DGM) are increasingly employed in emergent communication
systems. However, their application in multimodal data contexts is limited. This study …
systems. However, their application in multimodal data contexts is limited. This study …
A Survey on Emergent Language
The field of emergent language represents a novel area of research within the domain of
artificial intelligence, particularly within the context of multi-agent reinforcement learning …
artificial intelligence, particularly within the context of multi-agent reinforcement learning …
Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
R Ueda, T Taniguchi - arXiv preprint arXiv:2311.04453, 2023 - arxiv.org
As a sub-discipline of evolutionary and computational linguistics, emergent communication
(EC) studies communication protocols, called emergent languages, arising in simulations …
(EC) studies communication protocols, called emergent languages, arising in simulations …
Language Evolution with Deep Learning
Computational modeling plays an essential role in the study of language emergence. It aims
to simulate the conditions and learning processes that could trigger the emergence of a …
to simulate the conditions and learning processes that could trigger the emergence of a …
The curious case of representational alignment: Unravelling visio-linguistic tasks in emergent communication
Natural language has the universal properties of being compositional and grounded in
reality. The emergence of linguistic properties is often investigated through simulations of …
reality. The emergence of linguistic properties is often investigated through simulations of …
Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off
Artificial learners often behave differently from human learners in the context of neural agent-
based simulations of language emergence and change. A common explanation is the lack …
based simulations of language emergence and change. A common explanation is the lack …
Emergent communication for rules reasoning
Research on emergent communication between deep-learning-based agents has received
extensive attention due to its inspiration for linguistics and artificial intelligence. However …
extensive attention due to its inspiration for linguistics and artificial intelligence. However …
What makes a language easy to deep-learn?
Neural networks drive the success of natural language processing. A fundamental property
of language is its compositional structure, allowing humans to produce forms for new …
of language is its compositional structure, allowing humans to produce forms for new …
Revisiting populations in multi-agent communication
Despite evidence from sociolinguistics that larger groups of speakers tend to develop more
structured languages, the use of populations has failed to yield significant benefits in …
structured languages, the use of populations has failed to yield significant benefits in …