2 papers
cs.CL2024
The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
Seyed Parsa Neshaei, Yasaman Boreshban, Gholamreza Ghassem-Sani +1
Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks.…
cs.CL2021
Improving Question Answering Performance Using Knowledge Distillation and Active Learning
Yasaman Boreshban, Seyed Morteza Mirbostani, Gholamreza Ghassem-Sani +2
Contemporary question answering (QA) systems, including transformer-based architectures, suffer from increasing computational and model complexity which render them inefficient for…