2016/12/21 by Angeliki Lazaridou, Lazaridou, Angeliki, Alexander Peysakhovich +3 · 24 citations
Computer Science · Social Sciences · #Computation and Language (cs.CL) #Computer Science and Game Theory (cs.GT) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Language and cultural evolution #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Speech and dialogue systems #Topic Modeling #cs.CL #cs.CV #cs.GT #cs.LG #cs.MA
paper · pdf · doi:10.48550/arxiv.1612.07182
Accepted at ICLR 2017
openalex publication_date 2016/12/21 · arxiv created 2017/03/05 · arxiv updated 2017/03/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The current mainstream approach to train natural language systems is to expose them to large amounts of text. This passive learning is problematic if we are interested in developing interactive machines, such as conversational agents. We propose a framework for language learning that relies on multi-agent communication. We study this learning in the context of referential games. In these games, a sender and a receiver see a pair of images. The sender is told one of them is the target and is allowed to send a message from a fixed, arbitrary vocabulary to the receiver. The receiver must rely on this message to identify the target. Thus, the agents develop their own language interactively out of the need to communicate. We show that two networks with simple configurations are able to learn to coordinate in the referential game. We further explore how to make changes to the game environment to cause the "word meanings" induced in the game to better reflect intuitive semantic properties of the images. In addition, we present a simple strategy for grounding the agents' code into natural language. Both of these are necessary steps towards developing machines that are able to communicate with humans productively.