.png){kind=icon}
返回
Type affinity network for distantly supervised relation extraction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129684.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Distantly Supervised Relation Extraction (DSRE) focuses on mining relational information between entities from text, which is a critical step in constructing and expanding knowledge graphs. However, this task typically faces the problem of long-tail distribution of relationships. Furthermore, much previous research has been limited to specific relational features, overlooking the potential discriminative information in the dependencies among these features. To address these issues, we propose a Type Affinity Network (TAN) that explicitly models the dependencies among relational features. Using differentiated entity-type information and local context information, we extract high-quality feature representations. The dynamic integration of type dependency information via a type affinity matrix effectively leverages potential discriminative information, enhancing relation extraction accuracy. Furthermore, aggregating implicit features of relationships forms base points as references, improving the ability of the model to handle long-tail relations. These relationship base points differ from traditional hierarchical structures, providing amore general method. We conduct extensive experiments on two benchmark DSRE datasets, namely NYT-10 and WIKI-20 m. Compared with multiple state-of-the-art DSRE methods, the TAN not only shows significant performance improvements in handling long-tail relations, but also demonstrates overall performance improvement.
Keyword:
Type affinity matrix
Distant supervision
Relation extraction
Base point
Long tail
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Distantly supervised relation extraction with KB-enhanced reconstructed latent iterative graph networks基于KB增强的重构潜在迭代图网络的远距离监督关系提取
PREAI
分享收藏More refined superbag: Distantly supervised relation extraction with deep clustering.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏Semantic piecewise convolutional neural network with adaptive negative training for distantly supervised relation extractionNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏The Source, Spatial Distribution and Risk Assessment of Heavy Metals in Soil from the Pearl River Delta Based on the National Multi-Purpose Regional Geochemical SurveyPLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏分享收藏LTACL: long-tail awareness contrastive learning for distantly supervised relation extractionLTACL: 用于远程监督关系抽取的长尾意识对比学习OAAI
OAAI分享收藏
查看更多内容