research
∙
10/13/2021
Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning
Standard few-shot relation classification (RC) is designed to learn a ro...
share
research
∙
09/11/2021
Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
Few-shot slot tagging is an emerging research topic in the field of Natu...
research
∙
09/11/2021
TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
A multi-turn dialogue always follows a specific topic thread, and topic ...
research
∙
08/26/2021
MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
Meta-learning is widely used for few-shot slot tagging in the task of fe...
research
∙
11/17/2020