mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot

SLIM: EXPLICIT SLOT-INTENT MAPPING WITH BERT FOR JOINT bert 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 bert for joint intent classification and slot filling Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding in task-oriented systems

mad cars 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, and is trained