Výsledky vyhledávání - "Veiga, Álvaro"

Report

Using Zero-shot Prompting in the Automatic Creation and Expansion of Topic Taxonomies for Tagging Retail Banking Transactions

Autor: Moraes, Daniel de S., Santos, Pedro T. C., da Costa, Polyana B., Pinto, Matheus A. S., Pinto, Ivan de J. P., da Veiga, Álvaro M. G., Colcher, Sergio, Busson, Antonio J. G., Rocha, Rafael H., Gaio, Rennan, Miceli, Rafael, Tourinho, Gabriela, Rabaioli, Marcos, Santos, Leandro, Marques, Fellipe, Favaro, David

This work presents an unsupervised method for automatically constructing and expanding topic taxonomies using instruction-based fine-tuned LLMs (Large Language Models). We apply topic modeling and keyword extraction techniques to create initial topic

Externí odkaz: http://arxiv.org/abs/2401.06790

Zobrazit plný text záznamu

Report

Hierarchical Classification of Financial Transactions Through Context-Fusion of Transformer-based Embeddings and Taxonomy-aware Attention Layer

Autor: Busson, Antonio J. G., Rocha, Rafael, Gaio, Rennan, Miceli, Rafael, Pereira, Ivan, Moraes, Daniel de S., Colcher, Sérgio, Veiga, Alvaro, Rizzi, Bruno, Evangelista, Francisco, Santos, Leandro, Marques, Fellipe, Rabaioli, Marcos, Feldberg, Diego, Mattos, Debora, Pasqua, João, Dias, Diogo

This work proposes the Two-headed DragoNet, a Transformer-based model for hierarchical multi-label classification of financial transactions. Our model is based on a stack of Transformers encoder layers that generate contextual embeddings from two sho

Externí odkaz: http://arxiv.org/abs/2312.07730

Zobrazit plný text záznamu

Report

Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames

Autor: Busson, Antonio J G, Mendes, Paulo R C, Moraes, Daniel de S, da Veiga, Álvaro M, Guedes, Álan L V, Colcher, Sérgio

Recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG/MPEG compression technique. Most of them are built upon the processing made on the spatial dom

Externí odkaz: http://arxiv.org/abs/2010.05760

Zobrazit plný text záznamu

Report

Exploiting Low-Rank Structure in Semidefinite Programming by Approximate Operator Splitting

Autor: Souto, Mario, Garcia, Joaquim D., Veiga, Alvaro

In contrast with many other convex optimization classes, state-of-the-art semidefinite programming solvers are yet unable to efficiently solve large scale instances. This work aims to reduce this scalability gap by proposing a novel proximal algorith

Externí odkaz: http://arxiv.org/abs/1810.05231

Zobrazit plný text záznamu

Report

BooST: Boosting Smooth Trees for Partial Effect Estimation in Nonlinear Regressions

Autor: Fonseca, Yuri, Medeiros, Marcelo, Vasconcelos, Gabriel, Veiga, Alvaro

In this paper, we introduce a new machine learning (ML) model for nonlinear regression called the Boosted Smooth Transition Regression Trees (BooST), which is a combination of boosting algorithms with smooth transition regression trees. The main adva

Externí odkaz: http://arxiv.org/abs/1808.03698

Zobrazit plný text záznamu