Papers by Wei-Shinn Ku

1 papers
A Localized Geometric Method to Match Knowledge in Low-dimensional Hyperbolic Space (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for entity alignment are limited to Euclidean space and hyperbolic embedding can represent hierarchical structure in knowledge graphs.
Approach: They propose a localized geometric method to find equivalent entities in hyperbolic space using a hyperbolical neural network.
Outcome: The proposed method outperforms the state-of-the-art by a large margin.

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