Joint Intent Detection and Slot Filling Using Convolutional Neural Networks

We describe a joint model for intent detection and slot filling based on convolutional neural networks (CNN). The proposed architecture can be perceived as a neural network (NN) version of the triangular CRF model (TriCRF), which exploits the dependency between intents and slots, and models them simultaneously. Our slot filling component is a globally normalized CRF style model (as opposed to left-to-right models in recent NN based slot taggers), thus allowing the two tasks to share the same features extracted through CNN layers. We show that our slot model component generates state-of-the-art results, and our joint model outperforms the standard TriCRF by 1% absolute. On a number of other domains, our joint model achieves 0.7 1%, and 0.9 2.1% absolute gains over the independent modeling approach for intent and slot respectively.