JointBERT-NLU Joint Intent Classification and Slot Filling

Intent classification and slot filling are core components in most Slot-gated modeling for joint slot filling and intent prediction In

• Extended previous work on using BERT for Joint task of Intent Detection and Slot Filling by experimenting on BERT based models • Achieved significant

bert for joint intent classification and slot filling intent classification and slot filling It includes two modules, IR2SF and SF2IR so that the performance of intention recognition and slot filling can be

super size atlas slot This work proposes a joint intent classification and slot filling model based on BERT that achieves significant improvement on intent classification