Text Mining Under The Hood – are computers able to understand the human language

Professor Irena Spasić (University of Cardiff)

Cardiff University’s College of Physical Sciences and Engineering invites you to the next event in our inaugural Lecture Series, delivered by Professor Irena Spasić from the School of Computer Science & Informatics.

What does it take to understand a human language? Humans use two types of knowledge to make sense of written words: knowledge of language and that of the world. The ways in which we acquire such knowledge is the bone of contention between rationalism and empiricism. Rationalists, including Noam Chomsky, believe knowledge to be a product of innate features of the human mind, unlike empiricists who argue that knowledge is derived from experience alone. Where does that leave computers? Will they be ever able to truly understand our language? We will take a look into various ways computer programmes process written words and explore them from both perspectives. We will start from the bottom by explaining the binary code computers use to represent data (including text) and work our way up to the latest developments in language technology including deep learning.

Irena Spasić received a PhD degree in computer science from the University of Salford, UK in 2004. Following posts at the Universities of Belgrade, Salford and Manchester, she joined Cardiff School of Computer Science & Informatics in 2010, and became full professor in 2016. Her research interests include text mining, knowledge representation, machine learning and information management with applications in healthcare, life sciences and social sciences. She leads the text and data mining research theme at Cardiff University and is a co–founder of the UK Healthcare Text Analytics Research Network (HealTex).

Register here.