Learning to Compose Neural Networks for Question Answering
Title | Learning to Compose Neural Networks for Question Answering |
Publication Type | Journal Article |
Year of Publication | 2016 |
Authors | Andreas, J., Rohrbach M., Darrell T., & Klein D. |
Published in | CoRR |
Volume | abs/1601.01705 |
Abstract | 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. |
URL | http://www.icsi.berkeley.edu/pubs/vision/neuralnetqanda16.pdf |
ICSI Research Group | Vision |