wilker

I am a research associate in computational linguistics at the Institute for Logic, Language and Computation working on machine learning for natural language processing. Some of the problems I’ve looked into are machine translation, word alignment, textual entailment, paraphrasing, and question answering. My interests sit at the intersection of disciplines such as formal languages, machine learning, approximate inference, global optimisation, and computational linguistics.

Recently, I’ve developed quite an interest in Bayesian deep learning. In particular, I’m developing probabilistic neural network models that reason with and induce forms of discrete generalisation such as trees and graphs.

If you are looking for a project with me, you might want to start by joining one of our reading groups. I’ve put together a list of what I think may help one navigate through the landscape of deep generative models. And finally, I’ve made some technical notes available on github.

If you need to find me try Science Park 107 (F2.11).

News