Natural language processing (NLP) tasks can be addressed with several deep learning architectures, and many different approaches have proven to be efficient. This study aims to briefly summarize the use cases for NLP tasks along with the main architectures. This research presents transformer-based solutions for NLP tasks such as Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-Training (GPT) architectures. To achieve that, we conducted a step-by-step process in the review strategy: identify the recent studies that include Transformers, apply filters to extract the most consistent studies, identify and define inclusion and exclusion criteria, assess the strategy proposed in each study, and finally discuss the methods and architectures presented in the resulting articles. These steps facilitated the systematic summarization and comparative analysis of NLP applications based on Transformer architectures. The primary focus is the current state of the NLP domain, particularly regarding its applications, language models, and data set types. The results provide insights into the challenges encountered in this research domain.

Misinformation poses a significant challenge in the digital age, requiring robust methods to detect fake news. This study investigates the effectiveness of using Back Translation (BT) augmentation, specifically transformer-based models, to improve fake news detection in Romanian. Using a data set extracted from Factual.ro, the research finds that BT-augmented models show better accuracy, precision, recall, F1 score, and AUC compared to those using the original data set. Additionally, using mBART for BT augmentation with French as a target language improved the model’s performance compared to Google Translate. The Extra Trees Classifier and the Random Forest Classifier performed the best among the models tested. The findings suggest that the use of BT augmentation with transformer-based models, such as mBART, has the potential to enhance fake news detection. More research is needed to evaluate the effects in other languages.

The educational ontology we presented in this paper is used to model web-based e-learning systems for higher education. Our main objective was to create domain ontology to play an important role in representing higher education concepts and to assist specialized e-learning systems. We have stressed the need for developing educational models that meet the expectations of higher education community with regards to e-learning adaptation and efficiency by employing ontologies and Semantic Web techniques.

Dilated cardiomyopathy (DCM) represents a group of disorders affecting the structure and function of the heart muscle, leading to a high risk of heart failure and sudden cardiac death (SCD). DCM frequently involves an underlying genetic etiology. Genetic testing is valuable for risk stratification, treatment decisions, and family screening. Romanian population data on the genetic etiology of DCM are lacking. We aimed to investigate the genetic causes for DCM among Romanian adult patients at tertiary referral centers across the country. Clinical and genetic investigations were performed on adult patients presenting to tertiary hospitals in Romania. The genetic investigations used next-generation sequencing panels of disease-associated DCM genes. A total of 122 patients with DCM underwent genetic testing. The mean age at DCM diagnosis was 41.6 ± 12.4 years. The genetic investigations identified pathogenic or likely pathogenic variants in 50.8% of participants, while 25.4% had variants of unknown significance. Disease-causing variants in 15 genes were identified in people with DCM, with 31 previously unreported variants. Variants in TTN, LMNA, and DSP explained 75% of genetic causes for DCM. In total, 52.4% of patients had a family history of DCM/SCD. Left ventricular ejection fraction of <35% was observed in 41.9% of patients with disease-causing variants and 55% with negative or uncertain findings. Further genotype-phenotype correlations were explored in this study population. The substantial percentage (50.8%) of disease-causing variants identified in patients with DCM acknowledges the importance of genetic investigations. This study highlights the genetic landscape in genes associated with DCM in the Romanian population.

For indexing an image databases there are used many features. In this paper are used features like histograms for the color components, stochastic moments, few parameters of the co-occurrences matrix and the Gabor filters decomposition. Using all of them we obtain good performance in the field of content-based image indexing and retrieval. There are some speed problems because are many features used in the search process. Here, I present an algorithm for indexing and retrieval, which use a supervised tree algorithm for speed increasing. The area of applications is very wide: multimedia documents, transaction systems, medical application.

Information found nowadays on the World Wide Web is generally regarded as limitless. Hence emerged the need to find methods for organizing data in order to get better information retri ...