Catarina Silva
Catarina Silva has 4 papers in our library, in 2026, most of them on Information extraction, Named entity recognition, Language models & pretraining; often with Hugo Gonçalo Oliveira, Tomás Pinto.
OpenAlex · ORCID · Wikidata · h-index 23 · 189 works · 3,685 citations OpenAlex, 2026-10-14
Affiliations
Fields, topics and concepts
📚 Shelves 10The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 4 worksComputer Science · 4 worksArts and Humanities · 3 worksLanguage and Linguistics · 3 worksBiochemistry, Genetics and Molecular Biology · 1 workComputer Vision and Pattern Recognition · 1 workInformation Systems · 1 workLaw · 1 workMolecular Biology · 1 workSocial Sciences · 1 work
🧭 Topics 7Research subjects and languages the work is about.Information extraction · 2 worksEvaluation & benchmarks · 1 workInformation retrieval & search · 1 workLanguage models & pretraining · 1 workLegal AI · 1 workNamed entity recognition · 1 workQuestion answering · 1 work
Works by year
2020s
Papers
- Benchmarking Retrieval-Augmented Generation for Scientific Knowledge QA in European Portuguese (2026)
The paper asks whether retrieval-augmented generation helps small open language models answer scientific multiple-choice questions in European Portuguese (pt-PT), and how much the outcome depends on retrieval design. - Evaluating Generative Large Language Models for Portuguese Scientific Information Extraction (2026)
Scientific knowledge graphs (SciKGs) depend on reliable extraction of entities and relations from research papers. - Prompt Engineering for Named Entity Extraction from Portuguese Legal Documents (2026)
Supervised NER for Portuguese legal texts is limited because annotated corpora are scarce and expensive to build. - RelEx-PT: A Portuguese Sentence-Level Relation Extraction Dataset (2026)
Portuguese relation extraction lacks clean, controlled benchmarks. Existing resources tend to cover narrow domains, are skewed toward a few relations, target multi-sentence contexts, or depend on costly manual annotation. The authors address this with RelEx-PT, a natively Portuguese dataset in which each sentence has…
Co-authors here
Venues
- Natural Scientific Language Processing (NSLP) @ LREC ×2: Natural Scientific Language Processing (NSLP) @ LREC 2026 ×2
- Language Resources and Evaluation Conference (LREC): LREC 2026
- International Conference on Computational Processing of Portuguese: International Conference on Computational Processing of Portuguese 2026
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/catarina-silva/