@inproceedings{kottur-etal-2017-natural,
    title = "Natural Language Does Not Emerge {\textquoteleft}Naturally' in Multi-Agent Dialog",
    author = "Kottur, Satwik  and
      Moura, Jos{\'e}  and
      Lee, Stefan  and
      Batra, Dhruv",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D17-1321/",
    doi = "10.18653/v1/D17-1321",
    pages = "2962--2967",
    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 {\textquoteleft}negative' results culminating in a {\textquoteleft}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 {\textquoteleft}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."
}