Lexical Simplification (LS) automatically replaces difficult to read words for easier
alternatives while preserving a sentence's original meaning. LS is a precursor to Text …

To advance the neural decoding of Portuguese, in this paper we present a fully open
Transformer-based, instruction-tuned decoder model that sets a new state of the art in this …

Large language models (LLMs) have significantly advanced natural language processing,
but their progress has yet to be equal across languages. While most LLMs are trained in …

Sentiment Analysis (SA) can be applied to dialogues to determine the emotional tone
throughout the conversation. This is beneficial for dialogue systems because it may improve …

Abstract Despite advancements in Natural Language Processing (NLP) and the growing
availability of pretrained models, the English language remains the primary focus of model …

Automatically identifying hate speech is an emerging field driven by the growth of social
media and the consequent amplification of communication. However, this domain faces …

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 …

The automatic assessment of text readability and the classification of texts by levels is
essential for language education and languagerelated industries that rely on effective …

Even if technology has made legislative documents more accessible, they are often written
in jargon that makes them hard to understand for ordinary citizens, researchers, journalists …

This work investigates the application of Natural Language Processing (NLP) in the legal
context for the Portuguese language, emphasizing the importance of adapting pre-trained …