Dr. Yangqiu Song and PhD Student Huiru Xiao Received Outstanding Paper Award at AKBC 2021

In AKBC 2021, PhD student Huiru Xiao and Dr. Yangqiu Song, Assistant Professor of Department of Computer Science & Engineering and Department of Mathematics, received the Outstanding Paper Award for their co-authored paper "Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning".

The award-winning paper proposes learning the knowledge base embeddings in different geometric spaces and apply manifold alignment to align the shared entities. They evaluated the aligned embeddings on the out-of-taxonomy entity typing task, where they aim to predict the types of the entities from the knowledge graph. The experimental results on two datasets based on YAGO3 demonstrate that their approach has significantly good performances, especially in low dimensions and on small training rates. They revealed some future works include the exploration of broader types of geometries for learning embeddings and more effective approaches for aligning multiple manifolds are in progress.

Automated Knowledge Base Construction (AKBC) is a new conference focused on knowledge base construction including machine learning, natural language processing, computer vision, information integration, databases, search, data mining, knowledge representation, human computation, human-computer interfaces, and fairness. The AKBC conference serves as a research forum for all these areas, in both academia and industry.

Congratulations again to Dr. Song and Huiru!

For more details, please refer to the event website and the paper.