Short Bio

I am a postdoctoral researcher with Shimon Whiteson in the Whiteson Research Lab at the University of Oxford. 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 Fellowship 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.

Upcoming...

12/10/2017 I will be talking at the GPU Techonlogy Conference (GTC Europe) in Munich, Germany.
27/09/2017 I am a lecturer at the 2nd Internationael Summer School on Data Science (SSDS) and will talk about Deep Learning for Natural Language Processing.

News

04/09/2017 Our paper on End-to-end Differentiable Proving got accepted for oral presentation (1.2% acceptance rate) at NIPS 2017 in Long Beach, CA.
29/08/2017 Invited talk about End-to-end Differentiable Proving at Google Research in Mountain View, CA.
15/08/2017 I co-organized the 7th Workshop on Statistical Relational AI (StarAI) at UAI 2017 in Sydney, Australia.
26/07/2017 Invited talk about End-to-end Differentiable Proving at DeepMind.
14/06/2017 Invited talk about End-to-end Differentiable Proving at the South England Natural Language Processing Meetup.
07/06/2017 Invited 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 Invited 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

Selected Publications

End-to-end Differentiable Proving

NIPS 2017
Neural networks for end-to-end differentiable proving that learn vector representations of symbols and induce first-order logic rules.
NIPS oral presentation (1.2% acceptance rate).

Reasoning about Entailment with Neural Attention

ICLR 2016

Deep recurrent neural networks with attention mechanisms for recognizing textual entailment.

Programming with a Differentiable Forth Interpreter

ICML 2017

An end-to-end differentiable interpreter to train neural networks from program input-output data.

Adversarial Sets for Regularised Neural Link Predictors

UAI 2017

An adversarial model for regularizing neural networks by logical rules.

Injecting Logical Background Knowledge into Vector Representations

NAACL 2015

Differentiable logical rules for regularizing neural networks to incorporate background knowledge.

Contact

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

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