I am a PhD student in artificial intelligence at the University of Southampton. More specifically my research is in emergent communication, studying the development of language between autonomous agents. The agents train in an environment where communication is needed for success. However, no communication protocol is given, and few restrictions are placed on how the agents can communicate. The agents then develop a language from scratch, which is tailored to their observations. By creating their own language, agents can create shortcuts or simplified representations of complex concepts, making communication faster and more efficient. It also provides insights into human language evolution, by analysing what is needed for different aspects of language to emerge in controlled settings.
PhD in Artificial Intelligence
University of Southampton
BSc in Computer Science, 2016
University of Liverpool
Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.