Multi-domain Language Understanding of Task Oriented Dialogue Based on Intent Enhancement

The language understanding module in Task oriented Dialogue system includes two tasks: intent detection and slot filling. Typical joint language understanding models model the interaction between intent information and slot information through parameter sharing. These models may cause the problem that slot prediction values do not belong to the set of candidate slots under their corresponding intentions (This paper calls it slot field disorder). In order to reduce the impact of this problem, this paper proposed a joint model based on intent information enhancement. Intent information is explicitly introduced into the prediction process of slot location in the form of vectors. Three construction schemes of intent information vectors: bidirectional long-short term memory network, attention-based bidirectional long-short term memory network and convolutional neural network are successively tried. Finally, the experimental results on snips data set show that the joint model based on intent information enhancement has achieved 88.85%, 97.41% and 76.24% respectively in slot filling F-measure, intent recognition accuracy and semantic framework accuracy.