Continual relation extraction model based on memory sample selection and historical feature refinement

Zhanjun Zhang

doi:10.1016/j.asoc.2025.114485

2025-12-20

PRE

DOI：10.1016/j.asoc.2025.114485

原文链接

原文求助

摘要

En 中文

• 使用记忆样本和历史特征来增强CRE模型（CREMH）。 • 针对历史特征提出了一种精炼与集成表示方法。 • CREMH通过增强记忆样本的质量密度来缓解灾难性遗忘。 • CREMH在两个数据集上均优于基线方法，在总体和单类型得分上均表现更优。

期刊

Applied Soft Computing

IF:

6.6

论文数:

1.4W

被引数:

4.8W

机构

South-Central Minzu University

学者数:

841

论文数: 241

被引数: 0

Central China Normal University

学者数:

1.1W

论文数: 8.1K

被引数: 1.1W

Hefei University of Technology

学者数:

6.2K

论文数: 2.0K

被引数: 2.1W

查看更多机构

引用论文

Prompt-Based Prototypical Framework for Continual Relation Extraction

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING

IF5.1

2022-01-01

PREAI

Zhang, Han; Liang, Bin; Yang, Min; Wang, Hui; Xu, Ruifeng

Learning without Forgetting 学习不遗忘

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2018-12-01

OAAI

Zhizhong Li; Derek Hoiem

Overcoming catastrophic forgetting in neural networks 克服神经网络中的灾难性遗忘

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

IF9.1

2017-03-14

3.7K

OAAI

Kirkpatricka, James; Pascanu, Razvan; Rabinowitz, Neil; Veness, Joel; Desjardins, Guillaume; Rusu, Andrei A.; Milan, Kieran; Quan, John; Ramalho, Tiago; Grabska-Barwinska, Agnieszka; Hassabis, Demis; Clopath, Claudia; Kumaran, Dharshan; Hadsell, Raia

Document-level multiple relations extraction method via evidence guidance and relation correlation

APPLIED SOFT COMPUTING

IF6.6

2024-12-01

PREAI

Yang, Hao; Fu, Qiming; Lu, You; Wang, Yunzhe; Liu, Lanhui; Chen, Jianping

A joint entity and relation extraction framework for handling negative samples problems in named entity recognition

APPLIED SOFT COMPUTING

IF6.6

2025-01-01

PREAI

Zhang, Hongbin; Lin, Guangyu; Chen, Kezhou; Lin, Nankai; Cheng, Lianglun; Yang, Aimin