An Indigenous language could help humans and AI communicate
One of the most challenging problems impeding humans from communicating with Artificial Intelligence (AI) systems could have a unique solution: a language spoken by Indigenous Australians in the NT.
Researchers at the University of New South Wales have published a paper explaining how Jingulu - a language spoken by the Jingili people - could be translated directly into commands that both AI and humans can understand.
The study, published in Frontiers in Physics, details how Professor Abbass worked with linguistics expert Associate Professor Eleni Petraki and Dr Robert Hunjet, a member of the Defence Science and Technology Group to create JSwarm, a language inspired by Jingulu.
Jingulu uses just three verbs - come, go and do - which also means that the amount of computational power needed to understand the commands is low.
“For us, Jingulu is a dream that came true,” Professor Hussein Abbass, the study’s first author, said.
“A language that can translate straight into AI commands; a human language that humans can understand; an efficient language in its syntax that reduces computational cost; a language where we can change the context of use without changing its syntax to allow us to transfer the AI between different domains with ease; and a language that is born and used in Australia to support research and innovation that are born and used in Australia.”
Professor Abbass works with swarm systems of AI, where groups of robots work together to perform tasks and solve complex problems in a system that draws inspiration from how small numbers of sheepdogs can control large flocks of sheep.
“This problem is all about movements in different information and knowledge spaces, including the physical spaces,” Professor Abbass said.
“These movements are represented mathematically as elements that get attracted to each other or repulse from each other. For a long time, I have been looking at how we can design the languages used at the interface between the swarm and humans.”
Having previously investigated systems that rely on gestures, direct commands, and even music, Professor Abbass said these systems all had their challenges.
“They either had a richer language than what we needed or did not map exactly to the mathematics we use for guidance and control,” Dr Abbass said.
“This all changed one day when, out of curiosity, I was searching on Google for studies that looked at the syntax of Aboriginal languages.
“I encountered a PhD thesis about Jingulu, I started reading it then it did not take much time before it clicked in my head; this language would be perfect for my artificial intelligence-enabled swarm guidance work.”
This isn’t the first time Indigenous languages have been applied to interesting problems either, with applications dating back to World War II.
“The Aboriginal people have a long history of contributions to the defence of Australia,” Professor Abbass said.
“During the Second World War their languages were used for secret communications. Today we are discovering that the wealth and richness of the Aboriginal languages and culture could hold the secret in human-AI interaction.”
Image: Getty Images