A5066061053- Topic Modeling
- Natural Language Processing Techniques
- Biomedical Text Mining and Ontologies
- Data Quality and Management
- 3D Surveying and Cultural Heritage
- Communication and COVID-19 Impact
- BIM and Construction Integration
- AI in Service Interactions
- Seismology and Earthquake Studies
- Misinformation and Its Impacts
- Mobile Crowdsensing and Crowdsourcing
- Sentiment Analysis and Opinion Mining
- Disaster Management and Resilience
- Text Readability and Simplification
- Digital Transformation in Industry
- Context-Aware Activity Recognition Systems
- Public Relations and Crisis Communication
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento
2022
Iscte – Instituto Universitário de Lisboa
2020-2022
Instituto de Novas Tecnologias
2020
Institute for Systems Engineering and Computers
2020
The process of protecting sensitive data is continually growing and becoming increasingly important, especially as a result the directives laws imposed by European Union. effort to create automatic systems continuous, but, in most cases, processes behind them are still manual or semi-automatic. In this work, we have developed component that can extract classify data, from unstructured text information Portuguese. objective was system allows organizations understand their comply with legal...
Background In response to the intricate language, specialized terminology outside everyday life, and frequent presence of abbreviations acronyms inherent in health care text data, domain adaptation techniques have emerged as crucial transformer-based models. This refinement knowledge language models (LMs) allows for a better understanding medical textual which results an improvement downstream tasks, such information extraction (IE). We identified gap literature regarding LMs. Therefore,...
This paper presents DisBot, the first Portuguese speaking chatbot that uses social media retrieved knowledge to support citizens and first-responders in disaster scenarios, order improve community resilience decision-making. It was developed tested using Design Science Research Methodology (DSRM), being progressively matured with field specialists through several design development iterations. DisBot a state-of-the-art Dual Intent Entity Transformer (DIET) architecture classify user intents,...
This research is aimed at creating and presenting DisKnow, a data extraction system with the capability of filtering abstracting tweets, to improve community resilience decision-making in disaster scenarios. Nowadays most people act as human sensors, exposing detailed information regarding occurring disasters, social media. Through pipeline natural language processing (NLP) tools for text processing, convolutional neural networks (CNNs) classifying extracting knowledge graphs (KG) connected...
<sec> <title>BACKGROUND</title> In response to the intricate language, specialized terminology outside everyday life, and frequent presence of abbreviations acronyms inherent in health care text data, domain adaptation techniques have emerged as crucial transformer-based models. This refinement knowledge language models (LMs) allows for a better understanding medical textual which results an improvement downstream tasks, such information extraction (IE). We identified gap literature...
The rapid spread of COVID-19 around the world had a significant impact on daily life. As in other countries, measures were taken Portugal to combat exponential increase cases, such as curfews and use masks. Thus, parallel with direct consequences health healthcare sector, pandemic also caused changes human behavior from sociological viewpoint.
 objective this dissertation is attain perception reality concerning COVID-19. For purpose, real-time data was extracted three sources, two them...
2].O que distingue um Digital Twin (DT) de modelo BIM tradicional é a sua ligação fontes informação exteriores, com as quais troca dados.Assim,