Semantic Scholar Open Access 2017 234 sitasi

Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog

Satwik Kottur José M. F. Moura Stefan Lee Dhruv Batra

Abstrak

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, learned without any human supervision! In this paper, using a Task & Talk 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.

Topik & Kata Kunci

Penulis (4)

S

Satwik Kottur

J

José M. F. Moura

S

Stefan Lee

D

Dhruv Batra

Format Sitasi

Kottur, S., Moura, J.M.F., Lee, S., Batra, D. (2017). Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog. https://doi.org/10.18653/v1/D17-1321

Akses Cepat

Lihat di Sumber doi.org/10.18653/v1/D17-1321
Informasi Jurnal
Tahun Terbit
2017
Bahasa
en
Total Sitasi
234×
Sumber Database
Semantic Scholar
DOI
10.18653/v1/D17-1321
Akses
Open Access ✓