An Aboriginal language - spoken by only a few people in the Northern Territory - could hold the secret in the interaction between humans and artificial intelligence (AI).
Subscribe now for unlimited access.
$0/
(min cost $0)
or signup to continue reading
UNSW Canberra's Professor Hussein Abbass said the language - spoken by the Jingili people in an area between Renner Springs, Daly Waters and Wave Hill - could hold the key to solving some of the most challenging communication problems between humans and AI systems.
Dr Abbass' research paper, published by Frontiers in Physics, suggests the Jingulu language has characteristics that allow it to be easily translated into AI commands.
"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."
Professor Abbass said Jingulu was unique, even among Aboriginal languages, as it only used three verbs - come, go and do - to effectively communicate movements.
"For us, Jingulu is a dream that came true," the acting Deputy-Head of School with the School of Engineering and Information Technology at UNSW Canberra, said.
"A language that can translate straight into AI commands.
"A human language that humans can understand;
"A language that is born and used in Australia to support research and innovation that are born and used in Australia."
Professor Abbass' work involves AI 'agent swarms' that work together to solve complex problems or perform tasks.
"I am fascinated with trusted autonomy - a field that looks at designing safe and trustworthy interaction spaces between humans and smart Artificial-Intelligence-based machines.
"My particular interest is focusing on human-swarm interaction.
"For a long time, I have been looking at how we can design the languages used at the interface between the swarm and humans."
IN OTHER NEWS
The professor said he had tried systems that relied on gestures, direct commands and even music, but they 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, ... 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."
Working alongside University of Canberra linguistics expert and a member of the Defence Science and Technology group, Prof Abbass and his team created JSwarm, a language inspired by Jingulu.
The language can be applied to any situation where communication between humans and a large number of AI agents is required.
"Human languages ... have served humans effectively and efficiently," Prof Abbass paper said.
"Even within a single language, there could be many different varieties or codes, used by specific speaker groups, or maintained for particular contexts.
"These natural languages could be too inefficient for an AI enabled agent designed for a particular task or use, due to the languages being highly-complex, thus, creating a space of ambiguity or unnecessary complexity."
In his paper, Prof Abbass said human-human languages had a very long history, with studies that could be traced back to the ancient Greeks.
"AI-AI languages have its roots in recent literature, and have been a fruitful research area, whereby the languages could be emerging or designed."