no code implementations • 1 Feb 2024 • Nannan Huang, Haytham Fayek, Xiuzhen Zhang
In this study, using political bias as a case study, we first establish a methodology to quantify bias in abstractive models, then trace it from the pre-trained models to the task of summarising social media opinions using different models and adaptation methods.
no code implementations • 7 Jun 2023 • Nannan Huang, Lin Tian, Haytham Fayek, Xiuzhen Zhang
We found that BART and ChatGPT can better capture diverse opinions presented in the source documents.
no code implementations • 12 Dec 2020 • Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh, Haytham Fayek, Savitha Ramasamy, ArulMurugan Ambikapathi
Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters.