I am a PhD candidate in Informatics at LASIGE, Faculty of Sciences of the University of Lisbon (FCUL), currently a visiting PhD student at the Department of Computer Science, City St George’s, University of London.
My research is on neuro-symbolic approaches to ontology matching and knowledge graph alignment: combining learned representations with symbolic structure, and making the resulting alignments interpretable enough for domain experts to validate. I work on both the systems that produce alignments and the benchmarks used to evaluate them.
I am supervised by Cátia Pesquita (Associate Professor, FCUL) and Ernesto Jiménez-Ruiz (Senior Lecturer in Artificial Intelligence, City St George’s).
Since 2024 I have led the Bio-ML track of the Ontology Alignment Evaluation Initiative (OAEI), and I organise its new DISO track for 2026.
During my MSc I worked on deep reinforcement learning for n-way data analysis.
If you would like to collaborate, feel free to get in touch.
† denotes equal contribution
Dilworth, J.†, Giesteira Cotovio, P.†, Herron, D.†, Cripps, P., Dewdney, N., Pesquita, C., & Jiménez-Ruiz, E. (2026). Improving Interoperability among Defence and National Security Ontologies: Analysis and Evaluation Tasks. ISWC 2026, Accepted. [arXiv]
Giesteira Cotovio, P., Nunes, S., Jiménez-Ruiz, E., & Pesquita, C. (2026). Interpretable Context-Aware Models Improve Expert Validation in Ontology Matching. ESWC 2026, 234–257. [doi]
Balbi, L., Sousa, R. T., Cotovio, P., & Pesquita, C. (2026). The role of protein embeddings for protein–protein interaction prediction with graph neural networks. Briefings in Bioinformatics, 27(3), bbag313. [doi]
Rodrigues, A. F., Ferraz, L., Balbi, L., Giesteira Cotovio, P., & Pesquita, C. (2026). Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability. Scientific Reports, 16, 10974. [doi]
Monteiro Marques, J., Serrano, S., Selmi, H., Giesteira Cotovio, P., & Semedo-Lemsaddek, T. (2023). Antimicrobial and antibiofilm potential of Thymus vulgaris and Cymbopogon flexuosus essential oils against pure and mixed cultures of foodborne bacteria. Antibiotics, 12(3), 565. [doi]
Vasconcelos de Matos, L., Fernandes, L., Neves, M. T., Alves, F., Baleiras, M., Ferreira, A., Giesteira Cotovio, P., Dias Domingues, T., Malheiro, M., Plácido, A., Miranda, M. H., & Martins, A. (2021). From theory to practice: bone health in women with early breast cancer treated with aromatase inhibitors. Current Oncology, 28(2), 1067–1076. [doi]
Ferraz, L., Rodrigues, A. F., Cotovio, P., Ventura, M., Silva, G. H. G., Coroadinha, A. S., Machuqueiro, M., & Pesquita, C. (2026). Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids. [arXiv]
Dilworth, J., Lushnei, S., Shumsky, D., Shykula, S., Giesteira Cotovio, P., D’Avila Garcez, A., & Jiménez-Ruiz, E. (2026). Which Model, Which Prompt? Selecting and Configuring LLMs as Oracles for Ontology Matching. OM 2026. Accepted.
Abd Nikooie Pour, M., Blomqvist, E., Giesteira Cotovio, P., et al. (2025). Results of the Ontology Alignment Evaluation Initiative 2025. OM 2025. [CEUR]
Contreiras Silva, M., Faria, D., Cotovio, P., Ferraz, L., Balbi, L., & Pesquita, C. (2025). Matcha results in OAEI 2025. OM 2025. [CEUR]
Ferraz, L., Giesteira Cotovio, P., & Pesquita, C. (2025). Can Language Models Align Biomedical Ontologies? Evaluating Retrieval-Augmented Prompt Strategies in Bio-ML. SeWebMeDa 2025, co-located with ESWC 2025. [CEUR]
Abd Nikooie Pour, M., Algergawy, A., Blomqvist, E., et al., incl. Giesteira Cotovio, P. (2024). Results of the Ontology Alignment Evaluation Initiative 2024. OM 2024. [CEUR]
Faria, D., Contreiras Silva, M., Cotovio, P., Ferraz, L., Balbi, L., & Pesquita, C. (2024). Results in OAEI 2024 for Matcha. OM 2024, 110–117. [CEUR]
Faria, D., Contreiras Silva, M., Cotovio, P., Ferraz, L., Balbi, L., & Pesquita, C. (2023). Results for Matcha and Matcha-DL in OAEI 2023. OM 2023, 164–169. [CEUR]
Faria, D., Contreiras Silva, M., Cotovio, P., Eugénio, P., & Pesquita, C. (2022). Matcha and Matcha-DL results for OAEI 2022. OM 2022, 197–201. [CEUR]
EXACT-OM — main creator. Interpretable, context-aware ontology matching combining lexical similarity, relation-specific subgraph context and language-model signals, with visual and natural-language explanations of each decision.
Matcha — contributor since 2022; OAEI participant. I maintain the Python reimplementation, pymatcha.
LogMap — contributor since 2025. I maintain the Python reimplementation, pylogmap.
Ontology Alignment Evaluation Initiative — lead organiser of the Bio-ML track (2024–present); organiser of the new DISO track, Defence, Intelligence and Security Ontologies (2026).
Programme committee and reviewing (2026) — ESWC research track, ISWC resource track, NeSy main conference track, and the 2nd International Workshop on Explainable AI and Knowledge Graphs (XAI+KG @ ISWC 2026).
NeSy 2026 — organising volunteer.
Programming fundamentals, offered in the first year of seven bachelor programmes.
Computer networking fundamentals, offered in the second year of the BSc in Information Technology.
Ensemble learning, Markov models, deep learning and reinforcement learning, offered across all MSc programmes of the department.
Fundamentals of knowledge engineering, offered in the third year of the BSc in Informatics Engineering.
OutSystems fundamentals, in a course run with IEFP.
pedro.cotovio [at] city.ac.uk — pgcotovio [at] ciencias.ulisboa.pt