José Luís Oliveira

Also published as: José Luis Oliveira, Luís Oliveira


BioInfo@UAVR@SMM4H’22: Classification and Extraction of Adverse Event mentions in Tweets using Transformer Models
Edgar Morais | José Luis Oliveira | Alina Trifan | Olga Fajarda
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

This paper describes BioInfo@UAVR team’s approach for adressing subtasks 1a and 1b of the Social Media Mining for Health Applications 2022 shared task. These sub-tasks deal with the classification of tweets that contain an Adverse Drug Event mentions and the detection of spans that correspond to those mentions. Our approach relies on transformer-based models, data augmentation, and an external dataset.


BioinformaticsUA: Machine Learning and Rule-Based Recognition of Disorders and Clinical Attributes from Patient Notes
Sérgio Matos | José Sequeira | José Luís Oliveira
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)


BioinformaticsUA: Concept Recognition in Clinical Narratives Using a Modular and Highly Efficient Text Processing Framework
Sérgio Matos | Tiago Nunes | José Luís Oliveira
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)


Methodologies for Designing and Recording Speech Databases for Corpus Based Synthesis
Luís Oliveira | Sérgio Paulo | Luís Figueira | Carlos Mendes | Ana Nunes | Joaquim Godinho
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

In this paper we share our experience and describe the methodologies that we have used in designing and recording large speech databases for applications requiring speech synthesis. Given the growing demand for customized and domain specific voices for use in corpus based synthesis systems, we believe that good practices should be established for the creation of these databases which are a key factor in the quality of the resulting speech synthesizer. We will focus on the designing of the recording prompts, on the speaker selection procedure, on the recording setup and on the quality control of the resulting database. One of the major challenges was to assure the uniformity of the recordings during the 20 two-hour recording sessions that each speaker had to perform, to produce a total of 13 hours of recorded speech for each of the four speakers. This work was conducted in the scope of the Tecnovoz project that brought together 4 speech research centers and 9 companies with the goal of integrating speech technologies in a wide range of applications.


Morphosyntactic Disambiguation for TTS Systems
Ricardo Ribeiro | Luís Oliveira | Isabel Trancoso
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02)