Multi-Agent Cooperation and the Emergence of (Natural) Language
This work addresses the challenge of developing interactive conversational agents by moving beyond passive text exposure, though it is incremental as it builds on existing referential game paradigms.
The paper tackles the problem of passive language learning in AI by proposing a multi-agent communication framework using referential games, where agents develop their own language to coordinate, achieving successful coordination with simple networks and exploring methods to align the emergent language with intuitive semantics and ground it into natural language.
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.