`

Timezone: »

 
Poster
Teaching Machines to Read and Comprehend
Karl Moritz Hermann · Tomas Kocisky · Edward Grefenstette · Lasse Espeholt · Will Kay · Mustafa Suleyman · Phil Blunsom

Thu Dec 10 08:00 AM -- 12:00 PM (PST) @ 210 C #1
in Poster Session »

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

[ PDF] 

Author Information

Karl Moritz Hermann (Google DeepMind)
Tomas Kocisky (Google DeepMind)
Edward Grefenstette (Google DeepMind)
Lasse Espeholt (Google DeepMind)
Will Kay (Google DeepMind)
Mustafa Suleyman (Google DeepMind)
Phil Blunsom (Google DeepMind)

More from the Same Authors