Emergent Graphical Conventions in a Visual Communication Game
This research addresses the gap in studying emergent communication with sketches, offering a foundational step for AI and cognitive science, though it is incremental as it builds on prior work in emergent communication.
The paper tackles the problem of modeling the emergence of graphical conventions in visual communication by simulating two neural agents playing a sketching game, resulting in evolved sketches that preserve semantic continua and allow agents to switch between conventionalized and iconic communication based on familiarity.
Humans communicate with graphical sketches apart from symbolic languages. Primarily focusing on the latter, recent studies of emergent communication overlook the sketches; they do not account for the evolution process through which symbolic sign systems emerge in the trade-off between iconicity and symbolicity. In this work, we take the very first step to model and simulate this process via two neural agents playing a visual communication game; the sender communicates with the receiver by sketching on a canvas. We devise a novel reinforcement learning method such that agents are evolved jointly towards successful communication and abstract graphical conventions. To inspect the emerged conventions, we define three fundamental properties -- iconicity, symbolicity, and semanticity -- and design evaluation methods accordingly. Our experimental results under different controls are consistent with the observation in studies of human graphical conventions. Of note, we find that evolved sketches can preserve the continuum of semantics under proper environmental pressures. More interestingly, co-evolved agents can switch between conventionalized and iconic communication based on their familiarity with referents. We hope the present research can pave the path for studying emergent communication with the modality of sketches.