Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

natural-language-processing-2

Continual Relation Extraction

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in continual-relation-extraction-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find continual-relation-extraction-2 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

Cheng Jiayang, Deqing Yang, Yanghua Xiao, Li Cui, Jiaxin Yu, Chengwei Hu, Jingjie Yi•Thu Dec 31 2020

The proposed model outperforms the state-of-the-art CRE models and has great advantage in avoiding catastrophic forgetting, as well as utilizing the memory information sufficiently and efficiently, resulting in enhanced CRE performance.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Curriculum-Meta Learning for Order-Robust Continual Relation Extraction

Tongtong Wu, Yuan-Fang Li, Xuekai Li, Reza Haffari, G. Qi, Yujin Zhu, Guoqiang Xu•Tue Jan 05 2021

A novel curriculum-meta learning method is proposed to quickly adapt model parameters to a new task and to reduce interference of previously seen tasks on the current task to tackle catastrophic forgetting and order-sensitivity in continual relation extraction.

83 0

Paper Graph

Consistent Representation Learning for Continual Relation Extraction

Hua Xu, Kai Gao, Kang Zhao, Jian Yang•Fri Mar 04 2022

A consistent representation learning method is proposed, which maintains the stability of the relation embedding by adopting contrastive learning and knowledge distillation when replaying memory to alleviate forgetting effectively.

65 0

Paper Graph

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation

Sujian Li, Zhifang Sui, Tianyu Liu, Binghuai Lin, Yunbo Cao, Yifan Song, Peiyi Wang•Sun Oct 09 2022

This paper encourages the model to learn more precise and robust representations through a simple yet effective adversarial class augmentation mechanism (ACA), which is easy to implement and model-agnostic and can consistently improve the performance of state-of-the-art CRE models on two popular benchmarks.

32 0

Paper Graph

Enhancing Continual Relation Extraction via Classifier Decomposition

Zhifang Sui, Tianyu Liu, Binghuai Lin, Yunbo Cao, Heming Xia, Peiyi Wang•Sun May 07 2023

This work proposes a simple yet effective classifier decomposition framework that splits the last FFN layer into separated previous and current classifiers, so as to maintain previous knowledge and encourage the model to learn more robust representations at this training stage.

20 0

Paper Graph

Rationale-Enhanced Language Models are Better Continual Relation Learners

Weimin Xiong, Yifan Song, Sujian Li, Peiyi Wang•Mon Oct 09 2023

This work introduces rationale, i.e., the explanations of relation classification results generated by large language models (LLM), into CRE task and designs the multi-task rationale tuning strategy to help the model learn current relations robustly.

16 0

Paper Graph

Improving Continual Relation Extraction by Distinguishing Analogous Semantics

Wenzheng Zhao, Yuanning Cui, Wei Hu•Wed May 10 2023

This work designs memory-insensitive relation prototypes and memory augmentation to overcome the overfitting problem and introduces integrated training and focal knowledge distillation to enhance the performance on analogous relations.

30 0

Paper Graph

Adding a benchmark result helps the community track progress.

Continual Relation Extraction | State-of-the-Art