Short Bio

I am a postdoctoral researcher in the Whiteson Research Lab at University of Oxford's Department of Computer Science. Before, I was a PhD student in the Machine Reading group at University College London under the supervision of Sebastian Riedel. I am a recipient of a Google PhD Fellow in Natural Language Processing and a Microsoft Research PhD Scholarship.

My research focus is on machine learning models that learn reusable abstractions and that generalize from few training examples by incorporating various forms of prior knowledge. My work is at the intersection of deep learning, reinforcement learning, program induction, logic, and natural language processing.

I was fortunate to work as a Research Intern at Google DeepMind in Summer 2015 under the supervision of Edward Grefenstette. In 2012, I received my Diploma (equivalent to M.Sc) in Computer Science from the Humboldt-Universität zu Berlin. Between 2010 and 2012, I worked as a student assistant and in 2013 as research assistant in the Knowledge Management in Bioinformatics group of Ulf Leser.

I am co-organizer of the 7th UAI 2017 International Workshop on Statistical Relational AI (StarAI), the 1st NIPS 2016 Workshop on Neural Abstract Machines & Program Induction (NAMPI), and the 5th NAACL 2016 Workshop on Automated Knowledge Base Construction (AKBC), as well as scientific advisor for the London deep learning startup Bloomsbury AI.


15/08/2017 I am co-organizing the 7th Workshop on Statistical Relational AI (StarAI) at UAI 2017 in Sydney, Australia.
14/06/2017 Talk about End-to-end Differentiable Proving at the South England Natural Language Processing Meetup.
07/06/2017 Talk about End-to-end Differentiable Proving at the Future of Humanity Institute.


12/06/2017 Paper on Adversarial Sets for Regularising Neural Link Predictors got accepted at UAI 2017 in Sydney, Australia!
06/06/2017 I got interviewed by Matt Gardner and Waleed Ammar on the Allen Institute for Artificial Intelligence Podcast.
01/06/2017 Pre-print of our paper on End-to-end Differentiable Proving is online!
22/05/2017 Talk about End-to-end Differentiable Proving at the London Machine Learning Meetup.
13/05/2017 Paper on Programming with a Differentiable Forth Interpreter got accepted at ICML 2017 in Sydney, Australia!
02/05/2017 I joined the Whiteson Research Lab at University of Oxford as postdoctoral researcher.

News Archive


Neural Theorem Provers

arXiv 2017, AKBC 2016

Neural networks for end-to-end differentiable proving that learn vector representations of symbols and induce first-order logic rules.

Sequence Modeling

ICLR 2016, EMNLP 2016, ICRL 2017

Deep recurrent neural networks with attention mechanisms for recognizing textual entailment, Twitter stance detection, and language modeling.

Injecting Logical Background Knowledge into Vector Representations

EMNLP 2016, NAACL 2015

Differentiable logical rules for regularizing vector representations of symbols to incorporate background knowledge. Declarative, Functional Machine Learning

StarAI 2014

Scala domain-specific language for probabilistic and differentiable programming in a declarative and functional way.


Bioinformatics 2016, SemEval 2013, BioCreative 2013, Bioinformatics 2012

Probabilistic graphical models for bio-molecular event-extraction and named entity recognition of chemicals, mutations, proteins and diseases.


tim [dot] rocktaeschel [at] gmail [dot] com

Robert Hooke Building, Parks Road, Oxford OX1 3PR, United Kingdom