AI that can learn patterns of human language

News

The model automatically learns higher-level language patterns that can apply to different languages, enabling it to achieve better results
Published: 12Oct2022
Researchers have developed an artificial intelligence system that can learn the rules and patterns of human languages on its own. / Des chercheurs ont mis au point un système d’intelligence artificielle capable d’apprendre seul les règles et les structures des langues humaines.
Image by Jose-Luis Olivares, MIT.

Human languages are notoriously complex, and linguists have long thought it would be impossible to teach a machine how to analyze speech sounds and word structures in the way humans do. But researchers from McGill University, MIT, and Cornell University have taken a step in this direction. They have developed an artificial intelligence (AI) system that can learn the rules and patterns of human languages on its own.

The model automatically learns higher-level language patterns that can apply to different languages, enabling it to achieve better results. When given words and examples of how those words change to express different grammatical functions in one language – like tense, case, or gender – this machine-learning model comes up with rules that explain why the forms of those words change. For instance, it might learn that the letter “a” must be added to the end of a word to make the masculine form feminine in Serbo-Croatian.

This system could be used to put language theories to the test and investigate subtle similarities in the way diverse languages transform words, say the researchers. “We wanted to see if we can emulate the kinds of knowledge and reasoning that humans bring to the task,” says co-author Adam Albright, a professor of linguistics at MIT.

“The exciting thing about this work is that it shows how we can build algorithms that are able to generalize from really tiny samples of language data, more like human scientists and children,” says senior author Timothy O’Donnell, assistant professor in the Department of Linguistics at McGill University, and Canada CIFAR AI Chair at Mila - Quebec Artificial Intelligence Institute.

With files from MIT News Office

About this study

Synthesizing theories of human language with Bayesian program induction” by Kevin Ellis et al. was published in Nature Communications.


About McGill University

Founded in Montreal, Quebec, in 1821, McGill University is Canada’s top ranked medical doctoral university. McGill is consistently ranked as one of the top universities, both nationally and internationally. It is a world-renowned institution of higher learning with research activities spanning three campuses, 11 faculties, 13 professional schools, 300 programs of study and over 39,000 students, including more than 10,400 graduate students. McGill attracts students from over 150 countries around the world, its 12,000 international students making up 30% of the student body. Over half of McGill students claim a first language other than English, including approximately 20% of our students who say French is their mother tongue.

Contact Information

Contact: 
Shirley Cardenas
Organization: 
Media Relations, McGill University
Email: 
shirley.cardenas [at] mcgill.ca
Office Phone: 
(514) 398-6751
Back to top