Emergent Communication in a Multi-Modal, Multi-Step Referential Game
Katrina Evtimova, Andrew Drozdov, Douwe Kiela, Kyunghyun Cho
Abstract
Inspired by previous work on emergent communication in referential games, we propose a novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information exchange is bidirectional and of arbitrary duration. The multi-modal multi-step setting allows agents to develop an internal communication significantly closer to natural language, in that they share a single set of messages, and that the length of the conversation may vary according to the difficulty of the task. We examine these properties empirically using a dataset consisting of images and textual descriptions of mammals, where the agents are tasked with identifying the correct object. Our experiments indicate that a robust and efficient communication protocol emerges, where gradual information exchange informs better predictions and higher communication bandwidth improves generalization.
BibTeX
@inproceedings{
evtimova2018emergent,
title={Emergent Communication in a Multi-Modal, Multi-Step Referential Game},
author={Katrina Evtimova and Andrew Drozdov and Douwe Kiela and Kyunghyun Cho},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=rJGZq6g0-},
}