Related papers: Sabi\'a-4 Technical Report

We present and make available pre-trained language models (Phraser, Word2Vec, Doc2Vec, FastText, and BERT) for the Brazilian legal language, a Python package with functions to facilitate their use, and a set of demonstrations/tutorials…

Advances in speech and language technologies enable tools such as voice-search, text-to-speech, speech recognition and machine translation. These are however only available for high resource languages like English, French or Chinese.…

Speech technologies rely on capturing a speaker's voice variability while obtaining comprehensive language information. Textual prompts and sentence selection methods have been proposed in the literature to comprise such adequate phonetic…

The evaluation of Large Language Models (LLMs) in healthcare has been dominated by physician-centric, English-language benchmarks, creating a dangerous illusion of competence that ignores the interprofessional nature of patient care. To…

Speech-to-Speech (S2S) models have shown promising dialogue capabilities, but their ability to handle paralinguistic cues - such as emotion, tone, and speaker attributes - and to respond appropriately in both content and style remains…

The traditional teaching of software engineering is focused on technical skills. Active strategies, where students experience content and interact with reality, are effective. The market demands new skills in the digital transformation,…

This paper presents RigoBERTa, a State-of-the-Art Language Model for Spanish. RigoBERTa is trained over a well-curated corpus formed up from different subcorpora with key features. It follows the DeBERTa architecture, which has several…

Large language models (LLMs) and multi-agent orchestration are touted as the next leap in machine translation (MT), but their benefits relative to conventional neural MT (NMT) remain unclear. This paper offers an empirical reality check. We…

Automatic Speech recognition (ASR) is a complex and challenging task. In recent years, there have been significant advances in the area. In particular, for the Brazilian Portuguese (BP) language, there were about 376 hours public available…

As large language models (LLMs) develop anthropomorphic abilities, they are increasingly being deployed as autonomous agents to interact with humans. However, evaluating their performance in realistic and complex social interactions remains…

Recent advances in language modelling has significantly decreased the need of labelled data in text classification tasks. Transformer-based models, pre-trained on unlabeled data, can outmatch the performance of models trained from scratch…

Context: Software code review aims to early find code anomalies and to perform code improvements when they are less expensive. However, issues and challenges faced by developers who do not apply code review practices regularly are unclear.…

Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges:…

This paper introduces INACIA (Instru\c{c}\~ao Assistida com Intelig\^encia Artificial), a groundbreaking system designed to integrate Large Language Models (LLMs) into the operational framework of Brazilian Federal Court of Accounts (TCU).…

This paper investigates the finetuning of end-to-end models for bidirectional Estonian-English and Estonian-Russian conversational speech-to-text translation. Due to the limited availability of speech translation data for Estonian, we…

The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the…

Large Language Models (LLMs) can justify or critique their predictions through discussions with other models or humans, thereby enriching their intrinsic understanding of instances. While proactive discussions in the inference phase have…

Recent developments in online communication and their usage in everyday life have caused an explosion in the amount of a new genre of text data, short text. Thus, the need to classify this type of text based on its content has a significant…

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…

Recent advances in deep learning have promoted the advent of many computational systems capable of performing intelligent actions that, until then, were restricted to the human intellect. In the particular case of human languages, these…