Zobrazeno 1 - 10
of 1 949
pro vyhledávání: '"Fabio, G."'
Autor:
José, Marcos M., Cação, Flávio N., Ribeiro, Maria F., Cheang, Rafael M., Pirozelli, Paulo, Cozman, Fabio G.
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 Question Answering dataset for validation and training. One of the most comm
Externí odkaz:
http://arxiv.org/abs/2407.04858
Autor:
Pirozelli, Paulo, José, Marcos M., Filho, Paulo de Tarso P., Brandão, Anarosa A. F., Cozman, Fabio G.
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 investigate the extent to which encoder-only transformer language models
Externí odkaz:
http://arxiv.org/abs/2312.11720
Autor:
Pirozelli, Paulo, José, Marcos M., Silveira, Igor, Nakasato, Flávio, Peres, Sarajane M., Brandão, Anarosa A. F., Costa, Anna H. R., Cozman, Fabio G.
Pir\'a 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. This dataset represents a versatile language resource, particularly
Externí odkaz:
http://arxiv.org/abs/2309.10945
Publikováno v:
Neotropical Biology and Conservation, Vol 19, Iss 2, Pp 63-66 (2024)
A case of a non-fatal crocodile attack on a human was reported on the banks of the Segovia River on the Honduras and Nicaragua border. The 12-year-old girl survived the attack, only with damage to the tibia of her right leg, where she lost part of th
Externí odkaz:
https://doaj.org/article/9f1c36300afe453288f903aea8dbf3c1
Autor:
Mathias, Marlon S., de Barros, Marcel R., Coelho, Jefferson F., de Freitas, Lucas P., Moreno, Felipe M., Netto, Caio F. D., Cozman, Fabio G., Costa, Anna H. R., Tannuri, Eduardo A., Gomi, Edson S., Dottori, Marcelo
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 - S\~ao Vicente - Bertioga Estuarine System. PINN models aim to combine the
Externí odkaz:
http://arxiv.org/abs/2212.10681
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 Generation; it offers daily reports, news summaries and curious facts in Brazil
Externí odkaz:
http://arxiv.org/abs/2210.06431
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 proposed with an end-to-end deep learning flavor, which handles non-linguist
Externí odkaz:
http://arxiv.org/abs/2210.04107
Autor:
Pirozelli, Paulo, Castro, Ais B. R., de Oliveira, Ana Luiza C., Oliveira, André S., Cação, Flávio N., Silveira, Igor C., Campos, João G. M., Motheo, Laura C., Figueiredo, Leticia F., Pellicer, Lucas F. A. O., José, Marcelo A., José, Marcos M., Ligabue, Pedro de M., Grava, Ricardo S., Tavares, Rodrigo M., Matos, Vinícius B., Sym, Yan V., Costa, Anna H. R., Brandão, Anarosa A. F., Mauá, Denis D., Cozman, Fabio G., Peres, Sarajane M.
Publikováno v:
AI: Modeling Oceans and Climate Change (IJCAI-ECAI), 2022
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 Amazon. The "BLue Amazon Brain" (BLAB) integrates a number of services
Externí odkaz:
http://arxiv.org/abs/2209.07928
Autor:
Moreno, Felipe M., Netto, Caio F. D., de Barros, Marcel R., Coelho, Jefferson F., de Freitas, Lucas P., Mathias, Marlon S., Neto, Luiz A. Schiaveto, Dottori, Marcelo, Cozman, Fabio G., Costa, Anna H. R., Gomi, Edson S., Tannuri, Eduardo A.
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 predict the error of a numerical forecasting system developed for the Sa
Externí odkaz:
http://arxiv.org/abs/2208.05966
Autor:
Netto, Caio F. D., de Barros, Marcel R., Coelho, Jefferson F., de Freitas, Lucas P., Moreno, Felipe M., Mathias, Marlon S., Dottori, Marcelo, Cozman, Fábio G., Costa, Anna H. R., Gomi, Edson S., Tannuri, Eduardo A.
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 scenarios where the topographic map is complex, knowledge about the under
Externí odkaz:
http://arxiv.org/abs/2206.12746