最新

• A multi-task semantic decomposition framework with task-specific pre-training for few-shot ner
• A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition
• Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
• FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue
• Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations
• Value type-the bridge to a better DST model
• Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking
• PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling