Skip to content

Latest commit

 

History

History
20 lines (12 loc) · 816 Bytes

README.md

File metadata and controls

20 lines (12 loc) · 816 Bytes

Teaching Machines to Read and Comprehend

This repository contains an implementation of the models Teaching Machines to Read and Comprehend proposed by Karl Moritz Hermann and al., NIPS, 2015.

Models are implemented using Theano and Blocks. Datasets are implemented using Fuel.

Reference

Teaching Machines to Read and Comprehend, by Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman and Phil Blunsom, Neural Information Processing Systems, 2015.

Credits

Alex Auvolat

Thomas Mesnard

Étienne Simon