Capsule Networks for NLP

Capsule Networks were introduced in 2017 as in improvement over standard Convolutional Neural Networks in the paper Dynamic Routing Between Capsules. Capsule Networks aim to more effectively combine low-level features into higher-level features. Although originally designed to work with images, Capsule Networks have recently been applied to NLP tasks.

Read more about Capsule Networks and their recent adaptation to NLP from this blog post by Will Merrill!