Illustration of the BERT model for joint intent detection and slot filling

In addition, we demonstrate that joint training as well as the use of pre-trained lan- guage models, ELMo and BERT in our case, are complementary to these few-

BERT is used for intent recognition and slot filling because it effectively integrates the semantic information of intention and slot labels

bert slot In addition, we demonstrate that joint training as well as the use of pre-trained lan- guage models, ELMo and BERT in our case, are complementary to these few-

diamond 7 slot BERT, to develop a robust zero-shot slot filling model mcBERT uses BERT to initialize the two encoders, the query encoder and key encoder