April 3, 2024, 4:47 a.m. | Ryo Ueda, Tadahiro Taniguchi

cs.CL updates on arXiv.org arxiv.org

arXiv:2311.04453v2 Announce Type: replace
Abstract: As a sub-discipline of evolutionary and computational linguistics, emergent communication (EC) studies communication protocols, called emergent languages, arising in simulations where agents communicate. A key goal of EC is to give rise to languages that share statistical properties with natural languages. In this paper, we reinterpret Lewis's signaling game, a frequently used setting in EC, as beta-VAE and reformulate its objective function as ELBO. Consequently, we clarify the existence of prior distributions of emergent languages …

abstract agents arxiv beta communication computational cs.cl game key languages linguistics natural paper simulations statistical studies type vae word

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Sr. BI Analyst

@ AkzoNobel | Pune, IN