Toxic Text Classification in Portuguese: Is LLaMA 3.1 8B All You Need?

Citation:

Amanda Oliveira, Pedro H. Silva, Valéria Santos, Gladston Moreira, Vander L. Freitas, and Eduardo J. Luz. 2024. “Toxic Text Classification in Portuguese: Is LLaMA 3.1 8B All You Need?.” In Anais do XV Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana, Pp. 57–66. Porto Alegre, RS, Brasil: SBC.

Recent Publications

Fernando H. O. Duarte, Vander L.S. Freitas, Gladston Moreira, Eduardo Luz, and Leonardo B.L. Santos. 2023. “Correlations Between Epidemiological Time Series Forecasting and Influence Regions of Brazilian Cities.” In XXIV Brazilian Symposium on Geoinformatics - GEOINFO 2023, São José dos Campos, SP, Brazil, December 4-6, 2023, edited by Flávia F. Feitosa and Lúbia Vinhas, Pp. 340–345. MCTI/INPE. Publisher's Version

Pedro Castro, Gabriel Fortuna, Pedro Silva, Andrea G. C. Bianchi, Gladston Moreira, and Eduardo Luz. 2023. “Merging Traditional Feature Extraction and Deep Learning for Enhanced Hop Variety Classification: A Comparative Study Using the UFOP-HVD Dataset.” In Intelligent Systems, edited by Murilo C. Naldi and Reinaldo A. C. Bianchi, Pp. 307–322. Cham: Springer Nature Switzerland.Abstract

Accurately identifying plant species and varieties is crucial across various disciplines, such as biology, medicine, and agronomy. While species identification is challenging, variety identification presents an even greater difficulty. Conventional identification methods, although effective, often require specialized and costly equipment, making them less accessible. In this work, we explore the problem of hop variety classification, comparing traditional feature extraction methods with deep learning approaches using the UFOP-HVD dataset. We address two research questions: whether traditional techniques can achieve competitive results given the limited number of images and whether combining traditional techniques and deep learning can improve the current state-of-the-art. Our findings indicate that traditional techniques yield competitive results for hop variety identification, offering advantages such as interpretability, reduced computational costs, and potential integration into mobile devices. Moreover, we introduce an ensemble method that improves the accuracy from 77.16% to 81.90%, establishing a new state-of-the-art for the UFOP-HVD dataset. These results demonstrate the potential of merging traditional methods with deep learning for challenging hop variety classification tasks, providing an initial baseline for future research.

Lauro Moraes, Eduardo Luz, and Gladston Moreira. 2023. “Physicochemical Properties for Promoter Classification.” In Intelligent Systems, edited by Murilo C. Naldi and Reinaldo A. C. Bianchi, Pp. 368–382. Cham: Springer Nature Switzerland.Abstract

The accurate identification of promoter regions in DNA sequences holds significant importance in the field of bioinformatics. While this problem has garnered substantial attention in the literature, it remains unresolved. Several researchers have achieved notable outcomes by employing diverse machine-learning techniques to predict promoter regions. However, only a few have thoroughly explored the utilization of features derived from the physicochemical properties of DNA across various organism types. This study investigates the advantages of incorporating these features in the training of machine-learning models. The research evaluates and compares the performance of multiple metrics on diverse datasets encompassing both prokaryotic and eukaryotic organisms. The state-of-the-art CNNProm method is employed as the baseline for our experiments. The models and source code associated with this study can be accessed at the following URL of the project's repository: https://anonymous.4open.science/r/bracis-paper-1458/.