Eventos
DEFESA DE DISSERTAÇÃO DE MESTRADO Nº 303
Aluno: José Antônio Pedro dos Santos
Título: “Ulysses-HIRS: A Hybrid Information Retrieval System for Legislative Documents"
Orientador: Carmelo José Albanez Bastos Filho
Coorientadora: Ellen Polliana Ramos S. Pereira - (UFRPE)
Examinador Externo: Adriano Lorena Inácio Oliveira - (UFPE)
Examinador Interno: Cleyton Mário de Oliveira Rodrigues
Data-hora: 29 de Agosto de 2024, às 14:00.
Local: Formato remoto.
Resumo:
"The use of Transformers for text processing has attracted a large deal of attention in the last years. This is particularly true for sentence models, which present high capacity to comprehend and generate text contextually, improving the predictive performance in different Natural Language Processing tasks, when compared with previous approaches. Even so, there are still several chal- lenges when applied to long documents, especially for some knowledge areas with very specific characteristics, such as legislative proposals. Therefore, the Brazilian Portuguese language has complex constructions, and these features are even more relevant for legal texts. This study investigated different strategies for utilizing BERT-based models in long document retrieval written in Brazilian Portuguese. We used three corpora from the Brazilian Chamber of Deputies to build a dataset and assess the models, incorporating zero-shot and fine-tuning strategies. Five sentence models were evaluated: BERTimbau, LegalBert, LegalBert-pt, LegalBERTimbau, and LaBSE. We also assessed a summarized corpus of bills considering the input size limitation of the sentence models. Finaly, we propose developed a hybrid model, named Ulysses-HIRS, combining BM25 Large and BERTimbau with fine-tuning. According to the experimental results, the predictive performance obtained by Ulysses-HIRS was superior to the performance obtained by the other models, with a Recall of 84.78% for 20 documents."
DEFESA DE DISSERTAÇÃO DE MESTRADO Nº 302
Aluno: Roberto Sá Barreto Paiva da Cunha
Título: “Desenvolvimento de um Mecanismo de AutoML para Processamento de Dados em Larga Escala"
Orientador: Alexandre Magno Andrade Maciel
Coorientador: Jairson Barbosa Rodrigues - (UNIVASF)
Examinador Externo: Rosalvo Ferreira de Oliveira Neto - (UNIVASF)
Examinador Interno: Ivaldir Honório de Farias Junior
Data-hora: 23 de Agosto de 2024, às 15h.
Local: Formato Presencial, Sala de Atos (CSEC) - POLI/UPE (Recife/PE)-.
Resumo:
"A busca por simplificar a criação de modelos de aprendizado de máquina impulsiona o desenvolvimento da área de pesquisa referenciada por Aprendizado de Máquina Automatizado (Sigla em inglês: AutoML). Nas últimas duas décadas, diversos fenômenos sociais, econômicos e tecnológicos produziram um crescimento exponencial na geração de dados, aumentando a disponibilidade para treinamentos de modelos de AutoML. Entretanto, a maioria dos sistemas de AutoML de código aberto disponíveis possui limitações de processamento devido ao alto custo computacional de seus algoritmos e por serem baseados em escalabilidade vertical. Uma estratégia para contornar esta limitação consiste em utilizar arquitetura distribuída em Cluster e ferramentas para processamento e análise de big data. Nesse contexto, surge a necessidade da expansão da capacidade de processamento do Framework de Mineração de Dados (FMD) por meio de uma integração com Cluster. O desenvolvimento se deu por meio de pesquisa aplicada com caráter tecnológico baseado na metodologia Design Science Research, utilizando ferramentas de código aberto para big data como Apache Hadoop e Apache Spark. O projeto foi avaliado por meio de testes de integração, treinamento de modelos com dados reais e uma avaliação de especialistas."
DEFESA DE TESE DE DOUTORADO Nº 22
Aluno: Antonio Victor Alencar Lundgren
Título: “Development of a visual semantic analysis framework"
Orientador: Carmelo José Albanez Bastos Filho
Coorientador: Byron Leite Dantas Bezerra
Examinador Externo: Anthony Jose da Cunha C. Lins - (UNICAP)
Examinador Externo: Cleber Zanchetin - (UFPE)
Examinador Interno: Pablo Vinicius Alves de Barros
Examinador Interno: Bruno José Torres Fernandes
Data-hora: 02 de Agosto de 2024 às 9h.
Local: Formato remoto.
Resumo:
"Assistive robotics show the potential to alleviate the life of those most in need in our society, the ill, the elderly, or even the too-young, helping ease the burden of accomplishing common everyday tasks, securing environments, or even stimulating socialization through simulated companionship. Applications in assistive robotics usually make use of sensors to detect the ambient around them to aid in decision-making and task completion, and visual sensors are the most present among those, with cameras, lidars, and other devices helping the robots "see" around themselves. Recent advances in machine learning allowed those robots to achieve specific tasks with high levels of efficiency, with deep learning techniques as a highlight. However, those techniques are not capable of understanding or adapting to shifts in contexts, current literature lacks data, models, and even methodology capable of using the current advances in deep learning towards contextual understanding of tasks. Setting autonomous assistive robotics as the goal, this work taps the gap in machine learning for semantic analysis in visual tasks by creating a dataset to be used as a baseline for visual semantic analysis approaches, the HOD dataset, along with a framework for building and testing modular visual semantic analysis models to exploit state-of-the-art models and operations by the use of semantic variables. Semantic variables are secondary branches added to a model to extract contextual information, those branches can be any model for a specific output, unrelated to the tackled task. Those semantic variables are frozen, and their outputs are then merged with the main model’s outputs in an output head, helping the learning process by using complementary information. The HOD dataset is a novel object detection and dangerousness classification on indoor natural scenes, simulating the view of an NAO robot. It contains a total of 100,602 images and 435,753 annotated objects. We compare the use of a RetinaNet on the HOD dataset as a baseline, against the RetinaNet modified using the framework to attach a DenseNet161 as a semantic variable, this semantic variable pre-trained on the Places365 dataset to classify scenes. The model created and trained using the VisualSAF framework achieves a mean average precision of 0.834 and a mean average recall of 0.862 with intersection over union varying from 0.5 to 0.95 in steps of 0.05. Those results are 0.049 and 0.010 better than the baseline for mean average precision and mean average recall, respectively. This work also provides, as far as we know, the first definition of visual semantic analysis and categorization for its methodologies."
O Programa
