Moura and Kottur win Best Short Paper award at the 2017 EMNLP Conference

ECE Professor José Moura and Ph.D. student Satwik Kottur were recently recognized with the Best Short Paper award for their paper, "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog," at the 2017 Conference on Empirical Methods on Natural Language Processing (EMNLP).

Abstract
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.