no code implementations • 13 Apr 2024 • Melike Nur Yeğin, Mehmet Fatih Amasyali
Generative diffusion models showed high success in many fields with a powerful theoretical background.
no code implementations • 5 Apr 2024 • Gulsum Yigit, Mehmet Fatih Amasyali
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP).
no code implementations • 14 Feb 2024 • Himmet Toprak Kesgin, Mehmet Fatih Amasyali
The study concludes that the use of augmentation methods, especially in conjunction with MCCL, leads to improved results in various classification tasks, providing a foundation for future advances in text augmentation strategies in NLP.
no code implementations • 3 Jan 2024 • Himmet Toprak Kesgin, Mehmet Fatih Amasyali
Data augmentation is an effective technique for improving the performance of machine learning models.
no code implementations • 3 Jan 2024 • Himmet Toprak Kesgin, Mehmet Fatih Amasyali
SSL methods that use data augmentation are most successful for image datasets.
no code implementations • 26 Dec 2023 • Gulsum Yigit, Mehmet Fatih Amasyali
Integrating adversarial machine learning with Question Answering (QA) systems has emerged as a critical area for understanding the vulnerabilities and robustness of these systems.
no code implementations • 26 Jul 2023 • Himmet Toprak Kesgin, Muzaffer Kaan Yuce, Mehmet Fatih Amasyali
This study introduces and evaluates tiny, mini, small, and medium-sized uncased Turkish BERT models, aiming to bridge the research gap in less-resourced languages.
no code implementations • 1 Apr 2023 • Meltem Aksoy, Seda Yanik, Mehmet Fatih Amasyali
Appropriate reviewer assignment significantly impacts the quality of proposal evaluation, as accurate and fair reviews are contingent on their assignment to relevant reviewers.
1 code implementation • 19 May 2022 • M. Şafak Bilici, Mehmet Fatih Amasyali
The presented results show that, our model increases the performance of current models compared to other data augmentation techniques with a small amount of computation power.
1 code implementation • 26 Mar 2022 • Enes Dedeoglu, Himmet Toprak Kesgin, Mehmet Fatih Amasyali
SGD does not produce robust results on datasets with label noise.
no code implementations • ICLR 2018 • Melike Nur Mermer, Mehmet Fatih Amasyali
Studies in these topics show that starting with a small training set and adding new samples according to difficulty levels improves the learning performance.