Large Language Models and Concepts in Natural Language
PhD Candidate, University of Alberta (Ning Shi)
An examination of how large language models bridge lexical and sentence semantics through concepts, presenting recent findings and highlighting limitations in reasoning and multilingual contexts.
In this seminar from the Alberta Machine Intelligence Institute and the Department of Computing Science, Ning Shi and David Basil will present five recent publications on computational semantics. Across these studies, we hypothesize that concepts can serve as a bridge between lexical and sentence semantics, and large language models allow us to cross that bridge. Our results show connections among semantic tasks and reveal the limits of current models, especially in reasoning and multilingual contexts.
BIO: Ning Shi is a PhD candidate working with Prof. Grzegorz Kondrak. Before starting at the UofA, he worked as a senior algorithm engineer at Alibaba Group. Ning has graduate degrees from Georgia Tech, Syracuse University, and NYU. His doctoral research centers on establishing theoretical and computational connections between various semantic tasks in natural language processing, with the aim of enhancing their understanding and interpretability.