21 June 2019 - Tim Rocktäschel: Seminar

TITLE:

Learning with Explanations

ABSTRACT:

Despite the success of deep learning for a wide range of applications, this class of models suffers from two severe limitations: low sample efficiency and opaqueness. Low sample efficiency limits the application of deep learning to domains for which abundant training data exists whereas opaqueness prevents us from understanding how a model derives a particular output, let alone how to correct systematic errors, how to remove bias, or how to incorporate common sense and domain knowledge. To address these issues for knowledge base completion, we developed end-to-end differentiable provers. I will present our recent efforts in applying differentiable provers to statements in natural language texts and large-scale knowledge bases. Furthermore, I will introduce two datasets for advancing the development of models capable of incorporating natural language explanations: eSNLI, crowdsourced explanations for over half a million sentence pairs in the Stanford Natural Language Inference corpus, and ShARC, a conversational question answering dataset with natural language rules. Finally, based on our recent IJCAI survey I will give an outlook on how learning from natural language could hold the key for unlocking future advancements for agents that learn interactively in environments.

BIO:

Tim Rocktäschel is a Research Scientist at Facebook AI Research (FAIR) London and a Lecturer in the Department of Computer Science at University College London (UCL). At UCL, he is a member of the UCL Centre for Artificial Intelligence and the UCL Natural Language Processing group. Tim's research focuses on sample-efficient and more interpretable machine learning models that learn from world, domain, and commonsense knowledge in symbolic and textual form. His work is at the intersection of deep learning, reinforcement learning, natural language processing, program synthesis, and formal logic. Prior to joining FAIR and UCL, he was a Postdoctoral Researcher in the Whiteson Research Lab, a Stipendiary Lecturer in Computer Science at Hertford College, and a Junior Research Fellow in Computer Science at Jesus College, at the University of Oxford. Tim obtained his Ph.D. in the Machine Reading group at University College London under the supervision of Sebastian Riedel. He received a Google Ph.D. Fellowship in Natural Language Processing in 2017 and a Microsoft Research Ph.D. Scholarship in 2013. In Summer 2015, he worked as a Research Intern at Google DeepMind. In 2012, he obtained his Diploma (equivalent to M.Sc) in Computer Science from the Humboldt-Universität zu Berlin. Between 2010 and 2012, he worked as a Student Assistant and in 2013 as Research Assistant in the Knowledge Management in Bioinformatics group at the Humboldt-Universität zu Berlin. 

Add to your calendar

 vCal  iCal