Edward Grefenstette

Edward is a Research Scientist at Facebook AI Research (FAIR), and an Honorary Associate Professor (Reader) at UCL. He was previously a staff research scientist at DeepMind. Edward completed his DPhil (Ph.D.) at the University of Oxford, working on applying category-theoretic tools, initially developed to model quantum information flow, to model compositionality of distributed representations in natural language semantics. His recent research has covered topics at the intersection of deep learning and machine reasoning.

Edward's Publications

March 14, 2018

RESEARCH

Learning to Compute Word Embeddings On the Fly

Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare. Learning representations for words in the “long tail” of this distribution requires enormous amounts of data. Representations of rare…

Dzmitry Bahdanau, Tom Bosc, Stanislaw Jastrzebski, Edward Grefenstette, Pascal Vincent, Yoshua Bengio,

March 14, 2018

February 14, 2020

RESEARCH

RTFM: Generalizing to Novel Environment via Reading

Obtaining policies that can generalise to new environments in reinforcement learning is challenging. In this work, we demonstrate that language understanding via a reading policy learner is a promising vehicle for generalisation to new…

Victor Zhong, Tim Rocktäschel, Edward Grefenstette,

February 14, 2020