Zobrazeno 1 - 10
of 393
pro vyhledávání: '"Cardoso, Henrique"'
The electronic and magnetic properties of NdNiO$_3$ (NNO) thin films are very sensitive to epitaxial strain and to the proximity to ferromagnetic oxides. In this work, we investigate the structural, electronic, and magnetic properties of NdNiO$_3$/La
Externí odkaz:
http://arxiv.org/abs/2409.12270
As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the dev and devtest sets from Portuguese into Emakhuwa, and
Externí odkaz:
http://arxiv.org/abs/2408.11457
Question Answering (QA) datasets are crucial in assessing reading comprehension skills for both machines and humans. While numerous datasets have been developed in English for this purpose, a noticeable void exists in less-resourced languages. To all
Externí odkaz:
http://arxiv.org/abs/2406.04233
Autor:
Osório, Tomás, Leite, Bernardo, Cardoso, Henrique Lopes, Gomes, Luís, Rodrigues, João, Santos, Rodrigo, Branco, António
Leveraging research on the neural modelling of Portuguese, we contribute a collection of datasets for an array of language processing tasks and a corresponding collection of fine-tuned neural language models on these downstream tasks. To align with m
Externí odkaz:
http://arxiv.org/abs/2404.05333
Question Generation aims to automatically generate questions based on a given input provided as context. A controllable question generation scheme focuses on generating questions with specific attributes, allowing better control. In this study, we pr
Externí odkaz:
http://arxiv.org/abs/2404.02800
Autor:
Santos, Rodrigo, Rodrigues, João, Gomes, Luís, Silva, João, Branco, António, Cardoso, Henrique Lopes, Osório, Tomás Freitas, Leite, Bernardo
To foster the neural encoding of Portuguese, this paper contributes foundation encoder models that represent an expansion of the still very scarce ecosystem of large language models specifically developed for this language that are fully open, in the
Externí odkaz:
http://arxiv.org/abs/2403.01897
Question Generation (QG) is a task within Natural Language Processing (NLP) that involves automatically generating questions given an input, typically composed of a text and a target answer. Recent work on QG aims to control the type of generated que
Externí odkaz:
http://arxiv.org/abs/2306.14917
Available corpora for Argument Mining differ along several axes, and one of the key differences is the presence (or absence) of discourse markers to signal argumentative content. Exploring effective ways to use discourse markers has received wide att
Externí odkaz:
http://arxiv.org/abs/2306.04314
Autor:
Rodrigues, João, Gomes, Luís, Silva, João, Branco, António, Santos, Rodrigo, Cardoso, Henrique Lopes, Osório, Tomás
To advance the neural encoding of Portuguese (PT), and a fortiori the technological preparation of this language for the digital age, we developed a Transformer-based foundation model that sets a new state of the art in this respect for two of its va
Externí odkaz:
http://arxiv.org/abs/2305.06721
Autor:
Neves, Ana Luísa, Pereira, Ana Margarida, Bedbrook, Anna, Valiulis, Arunas, Jacomelli, Cristina, Azzolini, Elena, Parmelli, Elena, Canonica, Giorgio Walter, Zuberbier, Jaron, Vecillas, Leticia de las, Gilles, Louis, Leemann, Lucas, Klimek, Ludger, Ventura, Maria Teresa, Savoure, Marine, Dykewicz, Mark, Hofmann-Apitius, Martin, Papadopoulos, Nikolaos, Lourenço, Olga, Salmi, Sanna K., Williams, Sian, Palamarchuk, Yuliia, Torres, Maria Inês, Gil-Mata, Sara, Bognanni, Antonio, Ferreira-da-Silva, Renato, Yepes-Nuñez, Juan José, Lourenço-Silva, Nuno, Cardoso-Fernandes, António, Ferreira, André, Ferreira-Cardoso, Henrique, Portela, Diana, Teles, João, Kvedariene, Violeta, Torres, María Jose, Pfaar, Oliver, Brussino, Luisa, Zuberbier, Torsten, Fonseca, João A., Schünemann, Holger, Bousquet, Jean, Sousa-Pinto, Bernardo, Vieira, Rafael José
Publikováno v:
In The Journal of Allergy and Clinical Immunology: In Practice December 2024 12(12):3404-3418
