Zobrazeno 1 - 10
of 82
pro vyhledávání: '"AMASYALI, Mehmet Fatih"'
Publikováno v:
2024 Innovations in Intelligent Systems and Applications Conference (ASYU) published in IEEE Xplore
This paper investigates the effectiveness of BERT based models for automated punctuation and capitalization corrections in Turkish texts across five distinct model sizes. The models are designated as Tiny, Mini, Small, Medium, and Base. The design an
Externí odkaz:
http://arxiv.org/abs/2412.02698
The introduction of the Transformer neural network, along with techniques like self-supervised pre-training and transfer learning, has paved the way for advanced models like BERT. Despite BERT's impressive performance, opportunities for further enhan
Externí odkaz:
http://arxiv.org/abs/2407.00648
Publikováno v:
Neurocomputing Volume 608 , 1 December 2024, 128373
Generative diffusion models showed high success in many fields with a powerful theoretical background. They convert the data distribution to noise and remove the noise back to obtain a similar distribution. Many existing reviews focused on the specif
Externí odkaz:
http://arxiv.org/abs/2404.09016
Autor:
Yigit, Gulsum, Amasyali, Mehmet Fatih
Publikováno v:
SN Computer Science, 5, 506 (2024)
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We propose s
Externí odkaz:
http://arxiv.org/abs/2404.03938
This study conducts a thorough evaluation of text augmentation techniques across a variety of datasets and natural language processing (NLP) tasks to address the lack of reliable, generalized evidence for these methods. It examines the effectiveness
Externí odkaz:
http://arxiv.org/abs/2402.09141
Publikováno v:
2022 Innovations in Intelligent Systems and Applications Conference (ASYU), published in IEEE Xplore
Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use data augmentation are most successfu
Externí odkaz:
http://arxiv.org/abs/2401.01843
Publikováno v:
Communications in Computer and Information Science, vol. 1983, 450-463, Springer, 2023
Data augmentation is an effective technique for improving the performance of machine learning models. However, it has not been explored as extensively in natural language processing (NLP) as it has in computer vision. In this paper, we propose a nove
Externí odkaz:
http://arxiv.org/abs/2401.01830
Autor:
Yigit, Gulsum, Amasyali, Mehmet Fatih
Publikováno v:
Knowl Inf Syst (2024)
Integrating adversarial machine learning with Question Answering (QA) systems has emerged as a critical area for understanding the vulnerabilities and robustness of these systems. This article aims to comprehensively review adversarial example-genera
Externí odkaz:
http://arxiv.org/abs/2312.16156
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. We trained these models on a diverse dataset encompassing over 75GB of text from multi
Externí odkaz:
http://arxiv.org/abs/2307.14134
Publikováno v:
Journal of Artificial Intelligence Research 76 (2023) 761-827
Appropriate reviewer assignment significantly impacts the quality of proposal evaluation, as accurate and fair reviews are contingent on their assignment to relevant reviewers. The crucial task of assigning reviewers to submitted proposals is the sta
Externí odkaz:
http://arxiv.org/abs/2304.00353