.png){kind=icon}
.png){kind=icon}
Return
Structural entropy guided relation extraction on adaptive graph structure
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112789.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose the syntax graph and location graph to describe the relations of entities from different perspectives. • We propose the optimization strategy of graphs based on structural entropy to enhance the representation of entities and eliminate redundancies. • We propose the adaptive graph structure of entity pairs in the optimized graphs to construct the necessary local structure RE. • We conduct extensive experiments showing that our method outper forms previous works.