paper-with-me

Papers

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

2017-06-26 · Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra

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.

📄 PDF Abstract BibTeX arXiv:1706.08502

Code (3)

batra-mlp-lab/lang-emerge 공식 구현 pytorch
kdexd/lang-emerge-parlai pytorch
mcogswell/evolang pytorch

Similar Papers 제목 키워드 기반

Natural Language Does Not Emerge `Naturally' in Multi-Agent Dialog

2017-09-01 · EMNLP 2017 9 · Satwik Kottur, Jos{\'e} Moura, Stefan Lee, Dhruv Batra

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 Filling

Compositionality and Generalization in Emergent Languages

2020-04-20 · ACL 2020 6 · Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux 외

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 Learning

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

2025-10-28 · Yihao Li, Saeed Salehi, Lyle Ungar, Konrad P. Kording arxiv

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

2020-04-30 · ACL 2020 6 · Nur Geffen Lan, Emmanuel Chemla, Shane Steinert-Threlkeld

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

2020-11-30 · Niko A. Grupen, Daniel D. Lee, Bart Selman

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)