HuixingJiang

Latest

• ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement
• Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
• Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold
• Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
• Novel Slot Detection:A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System