Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, all learned without any human supervision! In this paper, using a Task and Tell reference game between two agents as a testbed, we present a sequence of 'negative' results culminating in a 'positive' one -- showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional. In essence, we find that natural language does not emerge 'naturally', despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.
Code (3)
Similar Papers 제목 키워드 기반
Natural Language Does Not Emerge `Naturally' in Multi-Agent Dialog
A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable …
Slot FillingCompositionality and Generalization in Emergent Languages
Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositionality}. In this paper, we study whether th…
DisentanglementRepresentation LearningDoes Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
Object binding, the brain's ability to bind the many features that collectively represent an object into a coherent whole, is central to human cognition. It groups low-level perceptual features into high-level object rep…
On the Spontaneous Emergence of Discrete and Compositional Signals
We propose a general framework to study language emergence through signaling games with neural agents. Using a continuous latent space, we are able to (i) train using backpropagation, (ii) show that discrete messages non…
Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems
In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to …
Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)