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, 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.- Anthology ID:
- D17-1321
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2962–2967
- Language:
- URL:
- https://aclanthology.org/D17-1321
- DOI:
- 10.18653/v1/D17-1321
- Cite (ACL):
- Satwik Kottur, José Moura, Stefan Lee, and Dhruv Batra. 2017. Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2962–2967, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog (Kottur et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D17-1321.pdf
- Code
- batra-mlp-lab/lang-emerge