Papers by Linan Yue

2 papers
RHGN: Relation-gated Heterogeneous Graph Network for Entity Alignment in Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for entity alignment fail to account for heterogeneity among KGs and distinction between KG entities and relations.
Approach: They propose a Relation-gated Heterogeneous Graph Network (RHGN) that uses a relation-gate based convolutional layer to distinguish relations and entities in the KG.
Outcome: Extensive experiments on four datasets show that the proposed method is superior to state-of-the-art methods.
Interventional Rationalization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for rationalization use spurious correlations in data to compose rationales and make predictions.
Approach: They propose a method to discover the causal rationales by using a structural causal model.
Outcome: The proposed method is based on the causal theory and validates on three real-world datasets.

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