Emergence of Symbols in Neural Networks for Semantic Understanding and Communication

These authors contributed equally to this work. Abstract The capacity to generate meaningful symbols and effectively employ them for advanced cognitive processes, such as communication, reasoning, and planning, constitutes a fundamental and distinctive aspect of human intelligence. Existing deep neural networks still notably lag human capabilities in terms of generating symbols for higher cognitive functions. Here, we propose a solution (symbol emergence artificial network (SEA-net)) to endow neural networks with the ability to create symbols, understand semantics, and achieve communication. SEA-net generates symbols that dynamically configure the network to perform specific tasks. These symbols capture compositional semantic information that allows the system to acquire new functions purely by symbolic manipulation or communication. We believe that the proposed framework will be instrumental in producing more capable systems that can synergize the strengths of connectionist and symbolic approaches for artificial intelligence (AI). MAIN TEXT Introduction Humans are a symbolic-based species (1). We can proficiently use symbols to understand and communicate about the external world and our internal state, as well as to reason about relationships and plan for actions (2, 3), thus providing humans with a decisive evolutionary advantage. Recently, large language models (LLMs) have demonstrated remarkable progress in sophisticated tasks of natural language processing (4, 5).