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 1–16 of 16 papers

TitleStatusHype
Consistent Representation Learning for Continual Relation ExtractionCode1
Enhancing Continual Relation Extraction via Classifier DecompositionCode1
Improving Continual Relation Extraction by Distinguishing Analogous SemanticsCode1
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
Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach—0
A Continual Relation Extraction Approach for Knowledge Graph Completeness—0
Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective—0
DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation—0
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild—0
Few-shot Continual Relation Extraction via Open Information Extraction—0
Improving Continual Relation Extraction through Prototypical Contrastive Learning—0
Preserving Generalization of Language models in Few-shot Continual Relation ExtractionCode0
Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation ExtractionCode0
Towards Rehearsal-Free Continual Relation Extraction: Capturing Within-Task Variance with Adaptive PromptingCode0
Show:102550

No leaderboard results yet.