SOTAVerified

Continual Relation Extraction

Compared with traditional relation extraction, CRE aims to help the model learn new relations while maintaining accurate classification of old ones.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 16 papers

TitleStatusHype
Enhancing Continual Relation Extraction via Classifier DecompositionCode1
Learning Robust Representations for Continual Relation Extraction via Adversarial Class AugmentationCode1
Curriculum-Meta Learning for Order-Robust Continual Relation ExtractionCode1
Rationale-Enhanced Language Models are Better Continual Relation LearnersCode1
Consistent Representation Learning for Continual Relation ExtractionCode1
Improving Continual Relation Extraction by Distinguishing Analogous SemanticsCode1
Preserving Generalization of Language models in Few-shot Continual Relation ExtractionCode0
Towards Rehearsal-Free Continual Relation Extraction: Capturing Within-Task Variance with Adaptive PromptingCode0
Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation ExtractionCode0
Improving Continual Relation Extraction through Prototypical Contrastive Learning—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.