A5047940958- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Topic Modeling
- Multi-Agent Systems and Negotiation
- Biomedical Text Mining and Ontologies
- Service-Oriented Architecture and Web Services
- Speech and dialogue systems
- Electronic Health Records Systems
- Logic, Reasoning, and Knowledge
- Mycobacterium research and diagnosis
- Infectious Diseases and Mycology
- Authorship Attribution and Profiling
- Artificial Intelligence in Law
- linguistics and terminology studies
- Constraint Satisfaction and Optimization
- Advanced Database Systems and Queries
- Advanced Text Analysis Techniques
- Artificial Intelligence in Healthcare
- Ginseng Biological Effects and Applications
- Video Analysis and Summarization
- Context-Aware Activity Recognition Systems
- Algorithms and Data Compression
- AI-based Problem Solving and Planning
- Library Science and Information Systems
- IoT and Edge/Fog Computing
University of Évora
2016-2025
Universidade Nova de Lisboa
2021-2025
National Institute of Health Dr. Ricardo Jorge
2022-2024
Centre for Artificial Intelligence and Robotics
2013-2017
Uninova
1992-1993
To explore information on the Semantic Web, SPARQL queries or DL-queries are suitable tools. However, users interested in exploring content of such knowledge bases often find it challenging to employ formal query languages, as this requires familiarity with target domain’s representation model. address these challenges, a Question-Answering System that automatically translates natural language questions into queries, over Smithsonian American Art Museum CIDOC-CRM is presented. The proposed...
This paper presents a strategy for the semantic migration of Portuguese National Archives records into CIDOC-CRM standard, an ontology developed museums, within context EPISA project. The approach to automatically populate is based on Mapping Description Rules semantically translate archives descriptive information representation. compliance model recommendations guarantees that populated verifies interoperability, and could be linked integrated with other ontologies. In modelling,...
We present a Question-Answering (QA) system for Portuguese juridical documents.The QA was applied to the complete set of decisions from several institutions (Supreme Courts, High Court, and Attorney-General's Office) in total 180,000 documents.
We propose a Cooperative Question Answering System that takes as input natural language queries and is able to return cooperative answer based on semantic web resources, more specifically DBpedia represented in OWL/RDF knowledge base WordNet build similar questions. Our system resorts ontologies not only for reasoning but also find answers independent of prior the resources by user. The question translated into its representation then answered consulting semantics sources information....
The Mycobacterium abscessus complex (MABC) is an emerging, difficult to treat, multidrug-resistant nontuberculous mycobacteria responsible for a wide spectrum of infections and associated with increasing number cases worldwide. Dominant circulating clones (DCCs) MABC have been genetically identified as groups strains higher prevalence, levels antimicrobial resistance, worse clinical outcomes. To date, little known about the genomic characteristics species in Portugal. Here, we examined...
To support an end to Question and Answering system help the clinical practitioners in a cardiovascular healthcare environment, extended discourse representation structure CIDERS is introduced. This extension of well-known DRT (Discourse Representation Theory) structures, go beyond single text extending them embrace general history given patient. Introduced proposed developed ontology framework, Ontology for General Clinical Practice, enhancing currently available state-of-the-art ontologies...
Question Answering systems that resort to the Semantic Web as a knowledge base can go well beyond usual matching words in documents and, preferably, find precise answer, without requiring user help interpret returned. In this paper, authors introduce Dialogue Manager that, through analysis of question and type expected provides accurate answers questions posed Natural Language. The not only represents semantics questions, but also structure discourse, including intentions context, adding...
In this paper discourse segments are defined and a method for segmentation primarily based on abduction of temporal relations between is proposed. This precise computationally feasible supported by previous work in the area anaphora resolution.
We propose a framework for collaborative legal information retrieval system based on dynamic logic programming. In order to be our keeps the context of interaction and tries infer user intentions. Each event is represented by programming facts which are used dynamically update previous model. User intentions inferred from this new model basis between texts knowledge base. As base we using documents Portuguese Attorney General (Procuradoria Geral da República). paper will show some examples...
A logic programming framework for the definition of cooperative multi-agent legal web information retrieval systems is proposed. Cooperation achieved through use dialogue processing techniques, namely, inference user intentions and existence a pro-active system behaviour, which tries to help users in their searches.