João Pedro Lebre Magalhães Pereira (9813-025F-6310)

Curriculum Vitae

João Pedro Lebre Magalhães Pereira

João L. M. Pereira holds a PhD from Instituto Superior Técnico, University of Lisbon (2023), and is certified for professor level positions in the Netherlands by the University of Amsterdam, the Basiskwalificatie Onderwijs (BKO) certification (2023). João is interested in Machine Learning (ML), Natural Language Processing (NLP), and Databases (DB), he made significance research in information extraction systems, acronym expansion, and user involvement in data cleaning. His noteworthy contributions include the publication of work on acronym expansion in the Proceedings of the Very Large Databases (Schimago Q1) in 2022, presented at the VLDB conference. Additional presentations on acronym disambiguation were presented in a workshop associated with the AAAI Conference on Artificial Intelligence. João's supervision led to the publication of two master's thesis works in workshops associated with the Conference on Empirical Methods in Natural Language Processing and the International Conference on Intelligent Data Engineering and Automated Learning. João has successfully coordinated four courses and participated as a Teaching Assistant for more than 10 different courses. He participated as supervisor for projects and Master thesis with companies and organizations such as Randstad, the Municipality of Amsterdam, and the fire department. Currently, as a researcher at the VISTA Lab, Algoritmi Center at the University of Évora, João participates in the EU Horizon funded project HarmonicAI and the development consulting project Awaken Moments funded by Empower Startups.

Read full resume ↓

Identification

Personal identification

Full name: João Pedro Lebre Magalhães Pereira

Citation names

João L. M. Pereira

Author identifiers

Ciência ID: 9813-025F-6310
ORCID iD: 0000-0002-3247-5524
Google Scholar ID: n9-ph6AAAAAJ&hl
Researcher Id: IYJ-9715-2023
Scopus Author Id: 57198007997

Knowledge fields

Engineering and Technology - Electrotechnical Engineering, Electronics and Informatics
Exact Sciences - Computer and Information Sciences - Information Science

Languages

Language	Speaking	Reading	Writing	Listening
Portuguese (Mother tongue)
English	Advanced (C1)	Advanced (C1)	Advanced (C1)	Advanced (C1)
Spanish; Castilian	Intermediate (B1)	Intermediate (B1)	Beginner (A1)	Intermediate (B1)

Education

	Degree	Classification
2016 - 2023/02/24 Concluded	Engenharia Informática e de Computadores (Doutoramento) Universidade de Lisboa Instituto Superior Técnico, Portugal "Towards effective and effortless data cleaning: from automatic approaches to user involvement" (THESIS/DISSERTATION)	Aprovado com Distinção
2014 Concluded	Master of Science (Technology) in Computer Science and Engineering (Master) Aalto-yliopisto, Finland "Supervised Learning for Relationship Extraction From Textual Documents " (THESIS/DISSERTATION)	3 (Finnish scale)
2013/11/11 Concluded	Engenharia Informática e de Computadores (Mestrado) Universidade de Lisboa Instituto Superior Técnico, Portugal "Supervised Learning for Relationship Extraction From Textual Documents" (THESIS/DISSERTATION)	16
2013 - 2013 Concluded	Scientific Writing and Communication - Short Course for Researchers (Curso médio) Universidade de Lisboa Instituto Superior Técnico, Portugal
2011 Concluded	Licenciatura Bolonha em Engenharia Informática e de Computadores - Alameda (Licenciatura) Universidade de Lisboa Instituto Superior Técnico, Portugal	14

Affiliation

Science

	Category Host institution	Employer
2015/07 - 2015/10	Research Trainee (Research)	Webdetials, a Pentaho Company, Portugal

Teaching in Higher Education

	Category Host institution	Employer
2024/09/16 - Current	Invited Assistant Professor (University Teacher)	Universidade de Évora, Portugal
	Universidade de Évora Departamento de Informática, Portugal
2023/09/12 - 2024/06/06	Invited Assistant Professor (University Teacher)	Universidade de Évora, Portugal
	Universidade de Évora Departamento de Informática, Portugal

Positions / Appointments

	Category Host institution	Employer
2021/08/23 - 2023/09	Teacher 4 (Lecturer)	Universiteit van Amsterdam Faculteit der Natuurwetenschappen Wiskunde en Informatica, Netherlands

Others

	Category Host institution	Employer
2015/10 - 2016/04	Engenheiro de software (Técnica Superior)	Webdetials, a Pentaho Company, Portugal

2015/01 - 2015/07	Investigador Junior (Investigação Científica)	Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvo, Portugal

2014/01 - 2014/12	Investigador Junior (Investigação Científica)	Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvo, Portugal

2013/03 - 2013/12	Investigador Junior (Investigação Científica)	Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvo, Portugal

Projects

Grant

	Designation	Funders
2018/09 - 2021/08	FCT PhD Scholarship SFRH/BD/135719/2018 PhD Student Fellow Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Fundação para a Ciência e a Tecnologia Concluded
2016 - 2018	ULisboa PhD Scholarship BD ULisboa PhD Student Fellow Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Concluded

Contract

	Designation	Funders
2024 - 2028	HarmonicAI: Human-guided collaborative multi-objective design of explainable, fair, and privacy-preserving AI for digital health 101131117 Researcher Universidade do Minho Centro ALGORITMI, Portugal Universidade de Évora, Portugal	Horizon Europe Excellent Science
2015/03/01 - 2021/04/01	Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa UID/CEC/50021/2019 SFRH/BPD/110695/2015 Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Fundação para a Ciência e a Tecnologia Concluded
2015/01/12 - 2015/07/12	Project DataStorm - Large-Scale Data Management in Cloud Environments EXCL/EEI-ESS/0257/2012 Research Fellow Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Fundação para a Ciência e a Tecnologia Concluded
2014/01/01 - 2014/12/31	Project DataStorm - Large-Scale Data Management in Cloud Environments EXCL/EEI-ESS/0257/2012 Research Fellow Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Fundação para a Ciência e a Tecnologia Concluded
2013/03/15 - 2013/12/15	SMARTIES PTDC/EIA-EIA/115346/2009 Research Fellow Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal	Fundação para a Ciência e a Tecnologia Concluded

Outputs

Publications

Conference paper	Berry Blom; João L. M. Pereira. "Domain Adaptation in Transformer Models: Question Answering of Dutch Government Policies". Paper presented in Intelligent Data Engineering and Automated Learning, Évora, 2023. 10.1007/978-3-031-48232-8_19 Lorincz, Anna; Graus, David; Lavi, Dor; João Pedro Lebre Magalhães Pereira. "Transfer learning for multilingual vacancy text generation". 2022. 10.18653/v1/2022.gem-1.18 Pereira, João Pedro Lebre Magalhães; Helena Galhardas; Bruno Martins. "A Benchmark for Relation Extraction Kernels". Paper presented in East-European Conference on Advances in Databases and Information Systems, Poitiers, 2015. Published • 10.1007/978-3-319-23135-8_13 Pereira, João Pedro Lebre Magalhães; Gonçalo Simões; Helena Galhardas; Bruno Martins. "Uma Benchmark para Kernels de Extracção de Relações". Paper presented in INFORUM, Porto, 2014. Published
Journal article	João L. M. Pereira; Manuel J. Fonseca; Antónia Lopes; Helena Galhardas. "Cleenex: Support for User Involvement During an Iterative Data Cleaning Process". Journal of Data and Information Quality (2024): http://dx.doi.org/10.1145/3648476. 10.1145/3648476 João Pedro Lebre Magalhães Pereira; João Casanova; Helena Galhardas; Dennis Shasha. "AcX: system, techniques, and experiments for acronym expansion". Proceedings of the VLDB Endowment 15 11 (2022): 2530-2544. http://dx.doi.org/10.14778/3551793.3551812. 10.14778/3551793.3551812
Report	Pereira, João Pedro Lebre Magalhães; Gonçalo Simões; Helena Galhardas; Bruno Martins. 2015. A Benchmark for Relation Extraction Kernels.
Thesis / Dissertation	"Towards effective and effortless data cleaning: from automatic approaches to user involvement". PhD, 2023. https://scholar.tecnico.ulisboa.pt/records/_9Wa_izOSPFA-ckoVSS5LrcEVDX-bgdZWHYy.

Activities

Supervision

	Thesis Title Role	Degree Subject (Type) Institution / Organization
2024 - 2024	Automating Character Network Extraction for Portuguese Literature Co-supervisor	Data-Driven Marketing (Master) Universidade NOVA de Lisboa NOVA Information Management School, Portugal
2024 - 2024	Network analysis of characters in portuguese literature Co-supervisor	Ciência de Dados e Métodos Analíticos Avançados (Master) Universidade NOVA de Lisboa NOVA Information Management School, Portugal
2023 - 2023	Enhancing Acronym Identification: Introducing a parentheses-free rule-based algorithm - ParenlessAI and a novel Bulgarian Data Set Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Summarization of Webpages to Generate Company Descriptions Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Long-Form Question Answering in the Dutch Municipal Domain Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Enhancing Topic Classification of Dutch Provincial Motions through Transfer Learning: A Comparative Analysis of Machine Learning Models Co-supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Using A Web Search Engine for Automatic Acronym Disambiguation Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Evaluating Large Language Models for Author Name Extraction in Noisy and Context-restricted Settings Co-supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2023 - 2023	Extraction of Acronyms and Expansions from Text using Machine Learning Methods Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Acronym identification techniques and experiments for acronym expander systems Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Acronym expansion in Dutch: Improving out-expansion performance with BERT and SBERT Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Acronym expansion for Spanish language Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Domain Adaptation in Transformer models: Question Answering of Dutch Government Policies Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Identifying football talent profiles: a feature reduction and cluster analysis Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2022 - 2022	Transfer learning for multilingual vacancy text generation Supervisor	Information Studies (Master) Universiteit van Amsterdam, Netherlands
2020 - 2021	Acronym and Definition Extraction Co-supervisor	Engenharia Informática e de Computadores (Master) Universidade de Lisboa Instituto Superior Técnico, Portugal

Event organisation

	Event name Type of event (Role)	Institution / Organization
2014 - 2014	Data Integration in the Life Sciences Conference (Other)	Fundação para a Ciência e a Tecnologia, Portugal
2014 - 2014	DataStorm Big Data Summer School Other (Other)	Fundação para a Ciência e a Tecnologia, Portugal

Event participation

	Activity description Type of event	Event name Institution / Organization
2023/11/22 - Current	Session Chair Conference	Intelligent Data Engineering and Automated Learning Universidade de Évora, Portugal

Jury of academic degree

	Topic Role	Candidate name (Type of degree) Institution / Organization
2024/10/29	Chemical Language Modeling. A Comparative Approach to SMILES and SELFIES Tokenization (Thesis) Main arguer	Miguelangel Augusto Leon Mayuare (Master) Universidade NOVA de Lisboa NOVA Information Management School, Portugal
2024/10/28	Improving Product Identification in Retail Industry using Computer Vision (Thesis) Main arguer	Gonçalo Figueiredo Alves Lopes (Master) Universidade NOVA de Lisboa NOVA Information Management School, Portugal
2024/10/28	Morality in Political Discourse in Portugal (Thesis) Main arguer	Jaime Olivio Teixeira Duarte (Master) Universidade NOVA de Lisboa NOVA Information Management School, Portugal
2023	An Experimental Evaluation of Cluster K Estimation Methods on Deep Learned Vector Embeddings for Page Stream Segmentation (Thesis) Main arguer	Eric Alfaro (Master) Universiteit van Amsterdam, Netherlands
2023	Testing for the efficacy and applicability of NLP approaches in capturing the dynamics of the British security environment between 2010 and 2021 (Thesis) Main arguer	Saskia Heyster (Master) Universiteit van Amsterdam, Netherlands
2023	Provenance and Dependency Analysis of Slide Decks (Thesis) Main arguer	Gargi Nandanpawar (Master) Universiteit van Amsterdam, Netherlands
2023	Recognizing Complex Named Entities Using GPT-3 (Thesis) Main arguer	Mark Geurts (Master) Universiteit van Amsterdam, Netherlands
2022	Information Retrieval and Knowledge Extraction on the Dutch Government Information Public Access Act Decision Letters (Thesis) Main arguer	Julián Venhuizen (Master) Universiteit van Amsterdam, Netherlands
2022	A comparison between two page-stream segmentation approaches using content evaluated on Dutch governmental data (Thesis) Main arguer	Stefan Dijkstra (Master) Universiteit van Amsterdam, Netherlands
2022	Combining Computer Vision and Deep Learning to split concatenated policy documents (Thesis) Main arguer	Sang Pham Minh (Master) Universiteit van Amsterdam, Netherlands
2022	Prediction of Post-Operative Esophagectomy Complications through Structured and Unstructured EHR Data (Thesis) Main arguer	Emily Bakker (Master) Universiteit van Amsterdam, Netherlands
2022	Improving readability and searchability of documents provided by the Dutch government under the WOB (Thesis) Main arguer	Justin Bon (Master) Universiteit van Amsterdam, Netherlands
2022	Detecting Redaction in publicly published government documents (Thesis) Main arguer	Ammar Alhashmi (Master) Universiteit van Amsterdam, Netherlands
2022	Generalisibility of deep learning page-stream segmentation methods evaluated on governmental data (Thesis) Main arguer	Pepijn Groenen (Master) Universiteit van Amsterdam, Netherlands
2022	Data structuring for climate change research: Carbon net-zero-specific label assignment to scientific documents (Thesis) Main arguer	Suvendu Pati (Master) Universiteit van Amsterdam, Netherlands
2022	Applying Dutch pre-trained word embedding models to classify grocery products (Thesis) Main arguer	Gijs Gubbels (Master) Universiteit van Amsterdam, Netherlands
2022	Using deep learned vector representations for page stream segmentation by agglomerative clustering (Thesis) Main arguer	Lukas Busch (Master) Universiteit van Amsterdam, Netherlands

Committee member

	Activity description Role	Institution / Organization
2024 - Current	Membro da Comissão Científica da Maratona Inter-Universitária de Programação - MIUP. A Maratona Inter-Universitária de Programação (MIUP) é um concurso anual de programação para estudantes universitários, inserido no ACM International Collegiate Programming Contest (2024). Member

Conference scientific committee

	Conference name	Conference host
2024 - 2024	Main-Track Program Committee member European Conference on Artificial Intelligence (ECAI)
2024 - 2024	Doctoral Consortium Program Committee member European Conference on Artificial Intelligence (ECAI)
2023/06/21 - 2023/06/23	International Conference on Computational Science	London, United Kingdom

Course / Discipline taught

	Academic session	Degree Subject (Type)	Institution / Organization
2014 - 2014	Java for Big Data	Especialização (Curso médio)	DataStorm Big Data Summer School, Portugal
2014 - 2014	Streaming Data Hands-On Lab Session	Especialização (Curso médio)	DataStorm Big Data Summer School, Portugal

Other jury / evaluation

	Activity description	Institution / Organization
2023 - Current	Membro do júri para a contratação de dois docentes em Sistemas de Informação na University of Amsterdam	Universiteit van Amsterdam, Netherlands

Distinctions

Award

2022	IST Excellent Teacher 2020/2021 Universidade de Lisboa Instituto Superior Técnico, Portugal
2012	3rd place in the EBEC Aalto Software Development Competition