[HTML][HTML] Performance analysis of long short-term memory predictive neural networks on time series data

R Bolboacă, P Haller - Mathematics, 2023 - mdpi.com
Long short-term memory neural networks have been proposed as a means of creating
accurate models from large time series data originating from various fields. These models …

Authorship Attribution in Less-Resourced Languages: A Hybrid Transformer Approach for Romanian

M Nitu, M Dascalu - Applied Sciences, 2024 - mdpi.com
Authorship attribution for less-resourced languages like Romanian, characterized by the
scarcity of large, annotated datasets and the limited number of available NLP tools, poses …

BERT-based Authorship Attribution on the Romanian Dataset called ROST

SM Avram - arXiv preprint arXiv:2301.12500, 2023 - arxiv.org
Being around for decades, the problem of Authorship Attribution is still very much in focus
currently. Some of the more recent instruments used are the pre-trained language models …

[PDF][PDF] Evaluation of Stylometry for Cross-Domain Authorship Attribution in Open Source Intelligence (OSINT)

F Klotz - 2024 - epub.technikum-wien.at
In the current digital world a lot of people actively participate in social media for
communication, interaction, and to share information. Users freely express their thoughts …

[PDF][PDF] Natural Language Processing Tools for Romanian–Going Beyond a Low-Resource Language

M Nitu, M Dascalu - ixdea.org
Advances in Natural Language Processing bring innovative instruments to the educational
field to improve the quality of the didactic process by addressing challenges like language …

[PDF][PDF] Text Classification using Term Co-occurrence Matrix

T Kovaliuk, I Yurchuk, K Dukhnovska, O Kovtun… - 2023 - ceur-ws.org
Among modern classification methods, the support vector machine occupies a leading place
due to its strict theoretical validity. This method is used in the theory of pattern recognition, in …