Events Calendar

PhD Thesis Defense - Kexuan Sun

Committee members: 
Prof. Jay Pujara
Prof. Aiichiro Nakano
Prof. Gerard Hoberg
 
Title: Advances in Understanding and Leveraging structured data for knowledge-intensive tasks   
 
Abstract:  Over the past few decades, the Web has evolved into an essential information hub. Among the vast repository of information, structured data, including well-organized tables, charts, and knowledge graphs, distinguishes itself as a valuable source of knowledge. This dissertation investigates techniques for understanding and harnessing such structured data to enhance knowledge-intensive applications. The first part of the dissertation focuses on tabular data. I first investigate approaches for understanding complex table structures by introducing an automated hybrid probabilistic system that identifies sub-structures within tables and their relationships, offering potential benefits for downstream tasks like data integration. I then explore approaches for selecting valuable information to answer questions relying heavily on financial tables. We approach this task by leveraging case-based reasoning, adapting solutions from existing questions to answer new questions effectively. The second part of the dissertation delves into the realm of KGs. I begin by investigating scientific KGs construction and empirically explore techniques that combine inherent graph structures and external entity-associated information. Additionally, I introduce a novel approach for accurately selecting important information from KGs to answer general-domain questions. These advances are necessary to fully exploit multi-source integrated systems that leverage unstructured and structured information together for knowledge delivery.    

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 203

Audiences: Everyone Is Invited

Contact: CS Events