Friday, 23rd June - 11am James Thorne : Seminar

Title:  Knowledge Issues and Language Models 

Abstract:

As we continue to push the boundaries of natural language processing, it becomes imperative to better understand how language models interact with, incorporate, and are influenced by knowledge. In this talk, I will navigate the complex interaction between language models and knowledge. 

I'll begin by presenting a forthcoming ACL paper, studying fact verification against knowledge graphs. This demonstrates the ability to ground language model outputs against structured information sources. Following this, I'll discuss ongoing research in multi-hop multi-set retrieval settings, and then explore how the abundance of knowledge available can potentially undermine retrieve-and-reason architectures. Lastly, I'll put forward a hypothesis about the role of knowledge in language models and consider the potential advantages of combining generative and retrieval-based NLP approaches.

Bio:  

James Thorne is Assistant Professor at the Korean Advanced Institute of Technology (KAIST).  James completed his PhD at the University of Cambridge where he developed models and methods for automated fact verification and correction under the direction of Andreas Vlachos and with the support of the Amazon Alexa Graduate Research Fellowship. James's research interests center around the issue of factuality in natural language processing, including how models, can access, reason with, and evaluate real-world knowledge.

Add to your calendar

 vCal  iCal