Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims
Author(s)
Meng, Kevin
Jimenez, Damian
Devasier, Jacob
Naraparaju, Sai Sandeep
Arslan, Fatma
Obembe, Daniel
Li, Chengkai
Journal
ACM Transactions on Intelligent Systems and Technology
Publisher
ACM
Citation
Kevin Meng, Damian Jimenez, Jacob Daniel Devasier, Sai Sandeep Naraparaju, Fatma Arslan, Daniel Obembe, and Chengkai Li. 2024. Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims. ACM Trans. Intell. Syst. Technol. Just Accepted (August 2024).
Version
Final published version
Abstract
This paper presents the latest developments to ClaimBuster?s claim-spotting model, which tackles the critical task of identifying check-worthy claims from large streams of information. We introduce the first adversarially-regularized, transformer-based claim-spotting model, which achieves state-of-the-art results on several bench-mark datasets. In addition to analyzing model performance metrics, we also quantitatively and qualitatively analyze the impact of ClaimBuster?s real-world deployment. Moreover, to help facilitate reproducibility and community engagement, we publicly release our codebase, dataset, data curation platform, API, Google Colab notebooks, and various ClaimBuster-based demo systems, at claimbuster.org.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3689212
