Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog
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)
Satwik Kottur
José M. F. Moura
Stefan Lee
Dhruv Batra
Akses Cepat
- Tahun Terbit
- 2017
- Bahasa
- en
- Total Sitasi
- 234×
- Sumber Database
- Semantic Scholar
- DOI
- 10.18653/v1/D17-1321
- Akses
- Open Access ✓