Projeto no LALIC

• Título do projeto: Meta-learning driven approach for transparent automated natural language processing

• Nível: Doutorado

• Breve descrição: This thesis addresses the challenges of Automated Machine Learning (AutoML) for Natural Language Processing (NLP) tasks, emphasizing the creation of models and facilitating the analysis, visualization, and interpretability of the results. Leveraging concepts from AutoML, the study explores meta-learning and hyperparameter optimization to develop a flexible and transparent approach – aiming to streamline the NLP pipeline and accommodate users with varying levels of expertise, from beginners to experts. As part of the contributions, it was developed MetaText-ClassifAI, an end-to-end AutoML framework for text classification that integrates data characterization, vectorization optimization, meta-learning, and automatic pipeline recommendation, achieving state-of-the-practice performance while reducing computational cost, execution time, and environmental impact, maintaining transparency and interpretability in the recommendation process. Furthermore, the work contributes with a analysis of the use of Large Language Models (LLMs) in NLP tasks, demonstrating that, although these models are effective for automating tasks such as exploratory data analysis, traditional statistical methods can still outperform modern LLM-based approaches in specific scenarios, achieving competitive performance with lower computational cost and greater efficiency.

• Agência financiadora: 

  • Americanas S.A. (2021-2023), CAPES (2023-2025)

• Orientadora:  Profa. Dra. Helena de Medeiros Caseli

• Co-orientador: Prof. Dr. Daniel Lucrédio

• Publicações decorrentes deste projeto:

  • Zagatti, F.R., Lucrédio, D., Caseli, H.d.M. (2025). Unsupervised Statistical Keyword Extraction Pipeline: Is LLM All You Need?. In: Paes, A., Verri, F.A.N. (eds) Intelligent Systems. BRACIS 2024. Lecture Notes in Computer Science(), vol 15413. Springer, Cham. https://doi.org/10.1007/978-3-031-79032-4_32

  • F. R. Zagatti, G. Yuuji Shimizu, D. Lucrédio and H. de Medeiros Caseli, "Investigating the Relationship Between Text Vectorization Cosine Similarity and Classification Performance," in IEEE Access, vol. 13, pp. 137348-137363, 2025, doi: 10.1109/ACCESS.2025.3595423. 

  • Zagatti, F.R. et al. (2026). LLM-Based Solution Applied to Explore Healthcare Datasets. In: Costin, HN., Magjarevic, R., Petroiu, GG. (eds) Advances in Digital Health and Medical Bioengineering II. EHB 2025. IFMBE Proceedings, vol 142. Springer, Cham. https://doi.org/10.1007/978-3-032-24724-7_53