Tracking the World State with Recurrent Entity Networks

12 Dec 2016Mikael Henaff • Jason Weston • Arthur Szlam • Antoine Bordes • Yann LeCun

It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. Like a Neural Turing Machine or Differentiable Neural Computer (Graves et al., 2014; 2016) it maintains a fixed size memory and can learn to perform location and content-based read and write operations. The EntNet sets a new state-of-the-art on the bAbI tasks, and is the first method to solve all the tasks in the 10k training examples setting.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering bAbi EntNet Accuracy (trained on 10k) 99.5% # 2
Question Answering bAbi EntNet Accuracy (trained on 1k) 89.1% # 2
Question Answering bAbi EntNet Mean Error Rate 9.7% # 2