Speaker: Loizos Michael, Open University of Cyprus
Title: Computational Perspectives on Story Understanding
Abstract:
Understanding a story often involves the completion of certain tasks, among which is the ability to identify the actors involved, the time-line of the story, the sequence of events that take place, etc. Humans are, as a matter of fact, rather competent at these tasks, being immersed in story-telling and story-understanding activities from an early age. Machines are slowly being endowed with this competence as well, as research in natural language processing advances over the years. One may, then, brave the question of whether we should be expecting, in the near future, to start reading bed-time stories to our personal computers, or sharing a good joke and a hearty laugh with them.
We shall discuss a fundamental aspect of story understanding that, we believe, is currently not well understood, and acts, for the time being, as a stumbling block in fully mechanizing story understanding: identifying hidden meaning in text. The talk will focus on two manifestations of this general theme, which relate, respectively, to how machines can (1) decide if a sequence of sentences constitutes a plausible story, and (2) draw those inferences from a story that a human would draw. We shall present two recently proposed theories for formally modeling, and making partial progress on, these two problems.
Short Bio:
Loizos Michael is a lecturer at Open University of Cyprus (since 2009). He is the founder and director of the Computational Cognition research lab (since 2010), and the academic head of a graduate program of studies in Information Systems (since 2011). Before joining OUC he held a visiting lecturer position at University of Cyprus (2008–2009). He was educated at University of Cyprus, where he received a B.Sc. in Computer Science with a minor degree in Mathematics (2002). He continued his education at Harvard University, where he received an M.Sc. and a Ph.D. in Computer Science (2003 and 2008, respectively).
His research focuses on the formal and principled understanding of cognitive processes such as learning and reasoning, and how those are employed by humans and other biological organisms in their everyday lives. Specific areas of interest include: commonsense reasoning, temporal and default reasoning, argumentation, computational learning theory, computational evolution theory, computational story understanding, nature-inspired computation, distributed and multi-agent systems.