1 code implementation • LREC 2022 • Gil Rocha, Luís Trigo, Henrique Lopes Cardoso, Rui Sousa-Silva, Paula Carvalho, Bruno Martins, Miguel Won
Interest in argument mining has resulted in an increasing number of argument annotated corpora.
no code implementations • 8 Apr 2024 • Tomás Osório, Bernardo Leite, Henrique Lopes Cardoso, Luís Gomes, João Rodrigues, Rodrigo Santos, António Branco
Similarly, the respective fine-tuned neural language models, developed with a low-rank adaptation approach, are made available as baselines that can stimulate future work on the neural processing of Portuguese.
1 code implementation • 3 Apr 2024 • Bernardo Leite, Henrique Lopes Cardoso
A controllable question generation scheme focuses on generating questions with specific attributes, allowing better control.
no code implementations • 4 Mar 2024 • Rodrigo Santos, João Rodrigues, Luís Gomes, João Silva, António Branco, Henrique Lopes Cardoso, Tomás Freitas Osório, Bernardo Leite
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 sense that they are open source and openly distributed for free under an open license for any purpose, thus including research and commercial usages.
1 code implementation • 21 Jun 2023 • Bernardo Leite, Henrique Lopes Cardoso
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.
no code implementations • 7 Jun 2023 • Gil Rocha, Henrique Lopes Cardoso, Jonas Belouadi, Steffen Eger
We demonstrate the impact of our approach on an Argument Mining downstream task, evaluated on different corpora, showing that language models can be trained to automatically fill in discourse markers across different corpora, improving the performance of a downstream model in some, but not all, cases.
no code implementations • 11 May 2023 • João Rodrigues, Luís Gomes, João Silva, António Branco, Rodrigo Santos, Henrique Lopes Cardoso, Tomás Osório
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 variants, namely European Portuguese from Portugal (PT-PT) and American Portuguese from Brazil (PT-BR).
no code implementations • WS 2019 • Gil Rocha, Henrique Lopes Cardoso
Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores.
no code implementations • WS 2019 • Jo{\~a}o Filgueiras, Lu{\'\i}s Barbosa, Gil Rocha, Henrique Lopes Cardoso, Lu{\'\i}s Paulo Reis, Jo{\~a}o Pedro Machado, Ana Maria Oliveira
Governmental institutions are employing artificial intelligence techniques to deal with their specific problems and exploit their huge amounts of both structured and unstructured information.
no code implementations • WS 2019 • Andr{\'e} Ferreira Cruz, Gil Rocha, Henrique Lopes Cardoso
Bias is ubiquitous in most online sources of natural language, from news media to social networks.
no code implementations • SEMEVAL 2019 • Andr{\'e} Cruz, Gil Rocha, Rui Sousa-Silva, Henrique Lopes Cardoso
On the main task, our model achieved an accuracy of 71. 7{\%}, which was improved after the task{'}s end to 72. 9{\%}.
1 code implementation • WS 2018 • Gil Rocha, Christian Stab, Henrique Lopes Cardoso, Iryna Gurevych
Argument mining aims to detect and identify argument structures from textual resources.