.png){kind=icon}
.png){kind=icon}
Return
An entity-relation extraction model based on bidirectional machine reading comprehension
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113885.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A relation extraction strategy based on machine reading comprehension is proposed. • Bidirectional extraction and assisted entity recognition avoid error accumulation. • Heterogeneous graph neural networks fully integrate semantic information. • The proposed model outperforms the state-of-the-art on several public datasets.
Keywords:
relation extraction
machine reading comprehension
entity recognition
graph neural networks
bidirectional extraction
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W