Emergent Communication of Generalizations
arXiv:2106.02668
Abstract
To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However, this often leads to successful but uninterpretable communication. We argue that this is due to the game objective: communicating about a single object in a shared visual context is prone to overfitting and does not encourage language useful beyond concrete reference. In contrast, human language conveys a rich variety of abstract ideas. To promote such skills, we propose games that require communicating generalizations over sets of objects representing abstract visual concepts, optionally with separate contexts for each agent. We find that these games greatly improve systematicity and interpretability of the learned languages, according to several metrics in the literature. Finally, we propose a method for identifying logical operations embedded in the emergent languages by learning an approximate compositional reconstruction of the language.
arXiv commentNeurIPS 2021
References in corpus (6)
- Prototypical Networks for Few-shot Learning
- Categorical Reparameterization with Gumbel-Softmax
- Multi-Agent Cooperation and the Emergence of (Natural) Language
- Compositional Obverter Communication Learning From Raw Visual Input
- ShapeWorld - A new test methodology for multimodal language understanding
- Emergent Multi-Agent Communication in the Deep Learning Era