SCS Faculty Candidate

  • Postdoctoral Researcher
  • Computational Cognitive Science Lab
  • University of California, Berkeley

Language Learning and Representation in Humans and Computers

Language is one of the greatest puzzles of both human and artificial intelligence (AI). Language learning happens effortlessly in children; yet, it is a complex process that we do not fully understand. Moreover, although access to more data and computation has resulted in recent advances in AI systems, they are still far from human performance in many language tasks. How do humans learn and represent language? And how can this inform AI?

In this talk, I first explain how computational modeling sheds light on the mechanisms underlying child word learning, which is an early step in language development. I introduce an unsupervised model that learns word meanings and their semantic connections using general cognitive mechanisms; the model processes data that approximates child input and assumes no built-in linguistic knowledge. I show that to account for child word learning, cognitive mechanisms such as memory and attention need to be integrated into the model's statistical learning.  Next, I explain how investigating human semantic processing helps us model semantic representations more accurately. I show that recent neural models of semantics, despite being trained on huge amount of data, fail at capturing important aspects of human similarity judgements. I also show that a probabilistic topic model does not have these problems, suggesting that exploring different representations may be necessary to capture different aspects of human semantic processing.

Aida Nematzadeh is a post-doctoral researcher at the University of California, Berkeley. She received a PhD and an MSc in Computer Science from the University of Toronto in 2015 and 2010, respectively. Aida’s research provides a better understanding of the computational mechanisms underlying the human ability to learn and organize information, with a focus on language learning. Aida has been awarded a NSERC Postdoctoral Fellowship from Natural Sciences and Engineering Research Council of Canada.

Machine Learning

For More Information, Please Contact: