8 citations · 26 across the 7 of their papers we have counts for
7 papers · 1 filter
Enhancing Portuguese Variety Identification with Cross-Domain Approaches
Hugo Sousa, Rúben Almeida, Purificação Silvano +3
Recent advances in natural language processing have raised expectations for generative models to produce coherent text across diverse language varieties. In the particular case of…
Tradutor: Building a Variety Specific Translation Model
Hugo Sousa, Satya Almasian, Ricardo Campos +1
Language models have become foundational to many widely used systems. However, these seemingly advantageous models are double-edged swords. While they excel in tasks related to res…
TEI2GO: A Multilingual Approach for Fast Temporal Expression Identification
Hugo Sousa, Ricardo Campos, Alípio Jorge
Temporal expression identification is crucial for understanding texts written in natural language. Although highly effective systems such as HeidelTime exist, their limited runtime…
Physio: An LLM-Based Physiotherapy Advisor
Rúben Almeida, Hugo Sousa, Luís F. Cunha +3
The capabilities of the most recent language models have increased the interest in integrating them into real-world applications. However, the fact that these models generate plaus…
GPT Struct Me: Probing GPT Models on Narrative Entity Extraction
Hugo Sousa, Nuno Guimarães, Alípio Jorge +1
The importance of systems that can extract structured information from textual data becomes increasingly pronounced given the ever-increasing volume of text produced on a daily bas…
A Biomedical Entity Extraction Pipeline for Oncology Health Records in Portuguese
Hugo Sousa, Arian Pasquali, Alípio Jorge +2
Textual health records of cancer patients are usually protracted and highly unstructured, making it very time-consuming for health professionals to get a complete overview of the p…
tieval: An Evaluation Framework for Temporal Information Extraction Systems
Hugo Sousa, Alípio Jorge, Ricardo Campos
Temporal information extraction (TIE) has attracted a great deal of interest over the last two decades, leading to the development of a significant number of datasets. Despite its…