20 citations · 52 across the 17 of their papers we have counts for
17 papers
A RAG-Based Institutional Assistant
Gustavo Kuratomi, Paulo Pirozelli, Fabio G. Cozman +1
Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documen…
Infusing Prompts with Syntax and Semantics
Anton Bulle Labate, Fabio Gagliardi Cozman
Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and seman…
Question Answering with Texts and Tables through Deep Reinforcement Learning
Marcos M. José, Flávio N. Cação, Maria F. Ribeiro +3
This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Questi…
Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks
Victor Hugo Nascimento Rocha, Igor Cataneo Silveira, Paulo Pirozelli +2
The recent success of Large Language Models (LLMs) has sparked concerns about their potential to spread misinformation. As a result, there is a pressing need for tools to identify…
Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models
Paulo Pirozelli, Marcos M. José, Paulo de Tarso P. Filho +2
Logical reasoning is central to complex human activities, such as thinking, debating, and planning; it is also a central component of many AI systems as well. In this paper, we inv…
Benchmarks for Pirá 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change
Paulo Pirozelli, Marcos M. José, Igor Silveira +5
Pirá is a reading comprehension dataset focused on the ocean, the Brazilian coast, and climate change, built from a collection of scientific abstracts and reports on these topics.…
A Multilingual Translator to SQL with Database Schema Pruning to Improve Self-Attention
Marcelo Archanjo Jose, Fabio Gagliardi Cozman
Long sequences of text are challenging in the context of transformers, due to quadratic memory increase in the self-attention mechanism. As this issue directly affects the translat…
Augmenting a Physics-Informed Neural Network for the 2D Burgers Equation by Addition of Solution Data Points
Marlon Sproesser Mathias, Wesley Pereira de Almeida, Marcel Rodrigues de Barros +9
We implement a Physics-Informed Neural Network (PINN) for solving the two-dimensional Burgers equations. This type of model can be trained with no previous knowledge of the solutio…
A Physics-Informed Neural Network to Model Port Channels
Marlon S. Mathias, Marcel R. de Barros, Jefferson F. Coelho +8
We describe a Physics-Informed Neural Network (PINN) that simulates the flow induced by the astronomical tide in a synthetic port channel, with dimensions based on the Santos - São…
BLAB Reporter: Automated journalism covering the Blue Amazon
Yan V. Sym, João Gabriel M. Campos, Fabio G. Cozman
This demo paper introduces the BLAB Reporter, a robot-journalist covering the Brazilian Blue Amazon. The Reporter is based on a pipeline architecture for Natural Language Generatio…
Comparing Computational Architectures for Automated Journalism
Yan V. Sym, João Gabriel M. Campos, Marcos M. José +1
The majority of NLG systems have been designed following either a template-based or a pipeline-based architecture. Recent neural models for data-to-text generation have been propos…
The BLue Amazon Brain (BLAB): A Modular Architecture of Services about the Brazilian Maritime Territory
Paulo Pirozelli, Ais B. R. Castro, Ana Luiza C. de Oliveira +19
We describe the first steps in the development of an artificial agent focused on the Brazilian maritime territory, a large region within the South Atlantic also known as the Blue A…
Enhancing Oceanic Variables Forecast in the Santos Channel by Estimating Model Error with Random Forests
Felipe M. Moreno, Caio F. D. Netto, Marcel R. de Barros +9
In this work we improve forecasting of Sea Surface Height (SSH) and current velocity (speed and direction) in oceanic scenarios. We do so by resorting to Random Forests so as to pr…
Modeling Oceanic Variables with Dynamic Graph Neural Networks
Caio F. D. Netto, Marcel R. de Barros, Jefferson F. Coelho +8
Researchers typically resort to numerical methods to understand and predict ocean dynamics, a key task in mastering environmental phenomena. Such methods may not be suitable in sce…
Pirá: A Bilingual Portuguese-English Dataset for Question-Answering about the Ocean
André F. A. Paschoal, Paulo Pirozelli, Valdinei Freire +8
Current research in natural language processing is highly dependent on carefully produced corpora. Most existing resources focus on English; some resources focus on languages such…
Integrating question answering and text-to-SQL in Portuguese
Marcos Menon José, Marcelo Archanjo José, Denis Deratani Mauá +1
Deep learning transformers have drastically improved systems that automatically answer questions in natural language. However, different questions demand different answering techni…
An Empirical Accuracy Law for Sequential Machine Translation: the Case of Google Translate
Lucas Nunes Sequeira, Bruno Moreschi, Fabio Gagliardi Cozman +1
In this research, we have established, through empirical testing, a law that relates the number of translating hops to translation accuracy in sequential machine translation in Goo…