skip to content

Department of Computer Science and Technology

Tuesday, 19 November, 2019 - 10:00 to 11:00
Adam Lopez (University of Edinburgh)
FW26, Computer Laboratory

Several datasets are now available that represent the meaning of natural language sentences. The semantic theories underlying these dataset often differ, but they are alike in that the representations all take the form of graphs. So, to properly model them in a machine learning system we need probabilistic models of graphs. Unfortunately, the space of generative probabilistic models of graphs is larger, weirder, and much less well explored than the space of generative models for strings. This talk will give you a guided tour of this space, including classical formalisms based on automata and grammars, and their more recent neural variants. It will cover work done in collaboration with Sorcha Gilroy, Federico Fancellu, Ieva Vasiljeva, Pijus Simonaitis, Sebastian Maneth, and Mirella Lapata.

Adam Lopez is a Reader at the University of Edinburgh with many research interests in natural language processing that are difficult to summarize.

Extra talk: note unusual day and time
NLIP Seminar Series

Upcoming seminars