Ease-of-Teaching and Language Structure from Emergent Communication
This addresses the problem of understanding language emergence in AI for researchers, but it appears incremental as it explores a new pressure within an existing framework.
The paper tackled the problem of how environmental pressures shape language structure in artificial agents by introducing a new pressure called ease of teaching, showing that it impacts the resulting language structure.
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the result of specific environmental pressures during training. By introducing new agents periodically to replace old ones, sequentially and within a population, we explore such a new pressure -- ease of teaching -- and show its impact on the structure of the resulting language.