Bernardo Leite

Home

Pineapple Hey! Welcome to my page.
Since childhood I have a big passion for computers and how they operate. Today I’m a fully motivated researcher and professional in the field of Computer Science. My main areas of interest are Artificial Intelligence, Natural Language Processing, Computer Supported Education and Question Generation (my PhD project). Feel free to contact me: bernardo.leite@fe.up.pt

Current Position(s)

PhD Candidate & Invited Assistent at Faculty of Engineering - University of Porto

Education

September 2015 - July 2020: Master of Science in Informatics and Computing Engineering

School: Faculty of Engineering - University of Porto
Course: Integrated Master in Informatics and Computer Engineering
Master Thesis: Automatic Question Generation for the Portuguese Language

Idioms

Portuguese (native language)
English (proficient)

Experience

Professional Activity

September 2023 - August 2024: Invited Assistent at Faculty of Engineering - University of Porto

1st Semester: Algorithms and Data Structures
2nd Semester: Algorithm Design

October 2021 - Current: PhD Student at Faculty of Engineering - University of Porto

Research Scope: Natural Language Processing (Question Generation)
Research Grant Institution: FCT

February 2021 - September 2021: Research Assistant at LIACC

Research Scope: Argumentation Mining
Project: DARGMINTS

May 2018 - August 2020: STEAM Educator at Happy Code Portugal

Unity - 2D and 3D Game Creating with C#
Fusion - Creating 2D Games
Minecraft Modding - Coding Games with Java
Apps - Creating Apps with MIT App Inventor
Youtuber - Planning, filming and editing

Achievements:

Personal fulfllment by entering the world of pedagogy - STEAM Education
Motivated Children’s Critical Thinking

Volunteering

July 3-7, 2023: Organizing volunteer at the 24th International Conference on Artifical Intelligence in Education (AIED) in Tokyo, Japan
July 2019 - May 2023: Organizer and Mentor of CoderDojo Valongo

Achievements:

Participating and Winning the contest: Orçamento Participativo Jovem 2019 (Valongo)
Promoting the exercise of citizenship with involvement, participation and learning
Planning and Coordinating an educational project for younger citizens

Service

July 15, 2024: Invited Speaker at DeepLearn 2024 in Maia - Porto, Portugal ("Empowering Research with LLMs: Case Studies and Insights")
July 11, 2023: Representative on behalf of the FEUP's Artificial Intelligence Laboratory at the DEI Open Day
June 1-2, 2022: Assistant organizer of the LITHME Roadshow in Porto, Portugal
Conference/Journal Reviewer:

Conference(s): EMNLP 23/24, ECAI 23, SAC 22/23, ISMIS 22, WI-IAT 21
Journal(s): JECR 21/22

Projects

bernardoleite.github.io: My personal Website made with HTML and CSS
question-generation-portuguese: Automatic Question Generation & Difficulty Control for the Portuguese Language (rule-based)
question-generation-t5-pytorch-lightning: Question Generation with T5 model using Transformers and Pytorch Lightning
question-answering-t5-pytorch-lightning: Question Answering with T5 model using Transformers and Pytorch Lightning
answer-extraction-and-qg: Tool for Answer Extraction and Question Generation
argument-density: Predicting Argument Density from Text
ArgMine Platform: Web-based platform for annotating argumentative text

Publications (selected)

(pre-print) Bernardo Leite, Tomás Freitas Osório, Henrique Lopes Cardoso. FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languages. ECTEL, 2024.

slides | code, data and models

Bernardo Leite, Henrique Lopes Cardoso. On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension. CSEDU, 2024.

Rodrigo Santos, João Rodrigues, Luís Gomes, João Silva, António Branco, Henrique Lopes Cardoso, Tomás Freitas Osório, Bernardo Leite. Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family. SIGUL @ LREC-COLING, 2024.

slides | data | models

Tomás Osório, Bernardo Leite, Henrique Lopes Cardoso, Luís Gomes, João Rodrigues, Rodrigo Santos, António Branco. PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese. BUCC @ LREC-COLING, 2024.

slides | data | models

Bernardo Leite, Henrique Lopes Cardoso. Towards Enriched Controllability for Educational Question Generation. AIED, 2023.

Bernardo Leite, Henrique Lopes Cardoso. Do Rules Still Rule? Comprehensive Evaluation of a Rule-Based Question Generation System. CSEDU, 2023.

Bernardo Leite, Henrique Lopes Cardoso. Neural Question Generation for the Portuguese Language: A Preliminary Study. EPIA, 2022.

(best paper award!) Gil Rocha, Bernardo Leite, Luís Trigo, Henrique Lopes Cardoso, Rui Sousa-Silva, Paula Carvalho, Bruno Martins, Miguel Won. Predicting Argument Density from Multiple Annotations. NLDB, 2022.

Afonso Sousa, Bernardo Leite, Gil Rocha, Henrique Lopes Cardoso. Cross-Lingual Annotation Projection for Argument Mining in Portuguese. EPIA, 2021.

Bernardo Leite, Henrique Lopes Cardoso, Luís Paulo Reis, Carlos Soares. Factual Question Generation for the Portuguese Language. INISTA, 2020.

Pedro Azevedo, Bernardo Leite, Henrique Lopes Cardoso, Daniel Castro Silva, Luís Paulo Reis. Exploring NLP and Information Extraction to Jointly Address Question Generation and Answering. AIAI, 2020.

...full publication list...