The 2019 Conference on Empirical Methods in Natural Language Processing And the 9th International Joint Conference on Natural Language Processing
Association for Computational Linguistics
There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions about the evolution of human language. However, optimizing deep architectures connected by a discrete communication channel (such as that in which language emerges) is technically challenging. We introduce EGG, a toolkit that greatly simplifies the implementation of emergent-language communication games. EGG¿s modular design provides a set of building blocks that the user can combine to create new games, easily navigating the optimization and architecture space. We hope that the tool will lower the technical barrier, and encourage researchers from various backgrounds to do original work in this exciting area.
Kharitonov, E.; Chaabouni, R.; Bouchacourt, D.; Baroni, M.. EGG: a toolkit for research on Emergence of lanGuage in Games. In: Huang, R.; Padó, S. (eds.). The 2019 Conference on Empirical Methods in Natural Language Processing And the 9th International Joint Conference on Natural Language Processing. 1 ed. East Stroudsburg PA: Association for Computational Linguistics; 2019. p. 55-60.