“Learning to Compose Neural Networks for Question Answering”, 2016-01-07 (; backlinks; similar):
We describe a question answering model that applies to both images and structured knowledge bases.
The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision.
Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains.