profile picture

Kevin Shabahang

1

presentations

SHORT BIO

I study knowledge representation and language acquisition from a statistical learning point-of-view. I am currently in the final stages of completing my doctorate at the University of Melbourne, under the supervision of Prof. Simon Dennis. For my PhD, I explored Hebbian associative learning models of lexical and compositional semantic processing using both connectionist modeling and behavioural experimentation. The theoretical and empirical basis of my exploration has been focused on the role of retrieval dynamics in structural generalization during comprehension, and has led to the development of a new spreading activation algorithm called the Dynamic Eigen Net. Most recently, I have co-founded a new AI startup called TimeCredit AI, as CTO, where Ndonga Sangia (CEO) and I are focusing on exploiting structure in accounting documents to help streamline the technical accounting workflow. I plan to continue my research into semantic processing, more independently outside of academia, through work focused on applying NLP techniques to the accounting domain.

Presentations

Constructing Word Meaning without Latent Representations using Spreading Activation

Kevin Shabahang

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved