Samuel Sousa - Academia.edu (original) (raw)

Papers by Samuel Sousa

Artificial Intelligence Review

Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, ... more Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union’s General Data Protection Regulation (GDPR), thereby enforce the need for privacy. Although many privacy-preserving NLP methods have been proposed in recent years, no categories to organize them have been introduced yet, making it hard to follow the progress of the literature. To close this gap, this article systematically reviews over sixty DL methods for privacy-preserving NLP published between 2016 and 2020, covering theoretical foundations, privacy-enhancing technologies, and analysis of their suitability for real-world scenarios. First, we introduce a novel taxonomy for classifying the existing methods into three categories: data safeguarding methods, trusted methods, and verification methods. Second, we present an extensive summary of privacy threats, datasets for applications, a...

Appeared in: Open Search Symposium 2021, 11-13 October 2021, CERN, Geneva, Switzerland.

This study evaluates the temporal effects of different methadone doses on isoflurane MAC in hens ... more This study evaluates the temporal effects of different methadone doses on isoflurane MAC in hens (Gallus gallus domesticus). Twelve healthy adult hens weighing 1.7 ± 0.2 kg had their individual MACs determined in a previous study using the bracketing technique via electrical stimulation (15V, 50 Hz and 6.5 ms). Birds were anesthetized with isoflurane diluted in 100% oxygen under controlled ventilation to maintain normocapnia. Each animal was maintained under a different fraction of its individual MAC (eg. 0.6 times MAC) and after 15 minutes 3 mg/kg IM of methadone was injected. Movement in response to the electrical stimulus was evaluated during one minute at 15-minute intervals after administration or until the bird moved in response. The reduction capacity of isoflurane MAC for each 15-minute interval was evaluated by logistic regression using a quantal dose-response curve and its jackknife SE was calculated. After at least a one-week interval, animals were anesthetized again and ...

Information Sciences, 2021

Abstract Word Sense Disambiguation (WSD) aims to determine the meaning of a word in context. Diff... more Abstract Word Sense Disambiguation (WSD) aims to determine the meaning of a word in context. Different approaches have been proposed in supervised and unsupervised domains. In most cases, supervised learning provides superior WSD performance. Since sense-annotated corpora can be difficult or time-consuming to obtain, which must be repeated for new domains, languages, and sense inventories, semi-supervised learning (SSL) methods, that combine a small amount of sense-annotated data, start to be pre-eminent. In SSL, graph-based methods are common, because they capture the relationships between terms using an undirected graph. This paper aims to investigate semi-supervised WSD by considering different graph-based SSL algorithms with features generated by word embeddings from Word2Vec, FastText, GloVe, BERT and ELECTRA models combined with parts-of-speech tags and word context. We test several combinations of word-embedding models, similarity measures for graph construction and SSL classification algorithms to disambiguate classical lexical sample WSD datasets. The results indicate our SSL algorithms achieved competitive results compared to supervised ones and the ELECTRA models performed better than other embeddings for SSL.

Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2019), 2020

The development of a housing prices prediction model can assist a house seller or a real estate a... more The development of a housing prices prediction model can assist a house seller or a real estate agent to make better-informed decisions based on house price valuation. Only a few works report the use of machine learning (ML) algorithms to predict the values of properties in Brazil. This study analyzes a dataset composed of 12,223,582 housing advertisements, collected from Brazilian websites from 2015 to 2018. Each instance comprises twenty-four features of five different data types: integer, date, string, float, and image. To predict the property prices, we ensemble two different ML architectures, based on Random Forest (RF) and Recurrent Neural Networks (RNN). This study demonstrates that enriching the dataset and combining different ML approaches can be a better alternative for prediction of housing prices in Brazil.

PloS one, 2016

The aim of this study was to measure the temporal effects of intramuscular methadone administrati... more The aim of this study was to measure the temporal effects of intramuscular methadone administration on the minimum anesthetic concentration (MAC) of isoflurane in hens, and to evaluate the effects of the isoflurane-methadone combination on heart rate and rhythm, blood pressure and ventilation. Thirteen healthy adult hens weighing 1.7 ± 0.2 kg were used. The MAC of isoflurane was determined in each individual using the bracketing method. Subsequently, the reduction in isoflurane MAC produced by methadone (3 or 6 mg kg-1, IM) was determined by the up-and-down method. Stimulation was applied at 15 and 30 minutes, and at 45 minutes if the bird had not moved at 30 minutes. Isoflurane MAC reduction was calculated at each time point using logistic regression. After a washout period, birds were anesthetized with isoflurane and methadone, 6 mg kg-1 IM was administered. Heart rate and rhythm, respiratory rate, blood gas values and invasive blood pressure were measured at 1.0 and 0.7 isofluran...