Yasaman Boreshban
YOU?
Author Swipe
View article: Less-supervised learning with knowledge distillation for sperm morphology analysis
Less-supervised learning with knowledge distillation for sperm morphology analysis Open
Sperm Morphology Analysis (SMA) is pivotal in diagnosing male infertility. However, manual analysis is subjective and time-intensive. Artificial intelligence presents automated alternatives, but hurdles like limited data and image quality …
View article: The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
The Impact of Quantization on the Robustness of Transformer-based Text Classifiers Open
Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of quantization on the…
View article: Deep Active Learning for Morphophonological Processing
Deep Active Learning for Morphophonological Processing Open
Seyed Morteza Mirbostani, Yasaman Boreshban, Salam Khalifa, SeyedAbolghasem Mirroshandel, Owen Rambow. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.
View article: RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems
RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems Open
Yasaman Boreshban, Seyed Morteza Mirbostani, Seyedeh Fatemeh Ahmadi, Gita Shojaee, Fatemeh Kamani, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processi…
View article: Improving Question Answering Performance Using Knowledge Distillation and Active Learning
Improving Question Answering Performance Using Knowledge Distillation and Active Learning Open
Contemporary question answering (QA) systems, including transformer-based architectures, suffer from increasing computational and model complexity which render them inefficient for real-world applications with limited resources. Further, t…