Papers by Shuhan Wu

1 papers
Towards Enhancing Relational Rules for Knowledge Graph Link Prediction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge graph reasoning methods are inadequate for missing knowledge . Various methods are explored to facilitate reasoning for missing information .
Approach: They propose a novel knowledge graph reasoning approach that uses a query-related fusion gate unit to model the sequentiality of relation composition and a buffering update mechanism to alleviate lagged entity information propagation.
Outcome: Experimental results show that the proposed approach is superior on both transductive and inductive link prediction tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations