Convolutional neural network based triangular CRF for joint intent detection and slot filling

Puyang Xu, Ruhi Sarikaya
2013 2013 IEEE Workshop on Automatic Speech Recognition and Understanding  
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), in which the intent label and the slot sequence are modeled jointly and their dependencies are exploited. Our slot filling component is a globally normalized CRF style model, as opposed to left-toright models in recent NN based slot taggers. Its features are automatically
more » ... re automatically extracted through CNN layers and shared by the intent model. We show that our slot model component generates state-of-the-art results, outperforming CRF significantly. Our joint model outperforms the standard TriCRF by 1% absolute for both intent and slot. 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.
doi:10.1109/asru.2013.6707709 dblp:conf/asru/XuS13 fatcat:a73relxbpnevpk3mpzalclfuwa