
I am an <a href='https://ellis.eu/phd-postdoc/' target='_blank'>ELLIS</a> PhD candidate (University of Lisbon and University of Amsterdam) supervised by <a href='https://andre-martins.github.io/' target='_blank'>André Martins</a> (Lisbon), <a href='https://vene.ro/' target='_blank'>Vlad Niculae</a> (Amsterdam), and <a href='https://wilkeraziz.github.io/' target='_blank'>Wilker Aziz</a> (Amsterdam). My PhD is funded by the ERC <a href="https://deep-spin.github.io/" target="_blank" rel="noreferrer">DeepSPIN Project</a>.

My Ph.D. thesis will be titled "Learnable Sparsity and Weak Supervision for Data-Efficient, Transparent, and Compact Neural Models" and defended in mid-2022. During my Ph.D. and in the context of this thesis, we have [published several papers](/publications) in top-tier venues (e.g. NeurIPS).

I did my MSc at The University of Edinburgh, where I studied Artificial Intelligence. My <a href='https://github.com/goncalomcorreia/vqa_human_attention' target='_blank'>Master's thesis</a> was advised by <a href='http://homepages.inf.ed.ac.uk/keller/' target='_blank'>Frank Keller</a> and was about using human attention as an additional supervision signal to improve the performance of a Visual Question Answering model.

I've been reviewer of several conferences over the years: ACL, EMNLP, NeurIPS, among others.


Cool Dish!

B.Sc. in Biomedical Engineering


In my B.Sc., I learned the foundations of engineering, mathematics, and physics,
along with medical related courses. During these years, I earned two Academic Merit awards.


Making Machines More Human: A Multitask Learning Approach to VQA and Human Attention Prediction

M.Sc. in Artificial Intelligence (Machine Learning)


In my M.Sc., I learned the foundations of Machine Learning, Deep Learning, and NLP.
Frank Keller advised my thesis, which was about using human attention as an additional supervision signal to improve the performance of a Visual Question Answering model.
I finished the degree with First Honors with Distinction.


Learnable Sparsity and Weak Supervision for Data-Efficient, Transparent, and Compact Neural Models

PhD in Electrical and Computer Engineering (Machine Learning)


My Ph.D. journey has not only taught me valuable skills in Machine Learning, Deep Learning, and Natural Language Generation but also to be self-taught and autonomous. I have published in top-tier venues during these years.


Summer Intern


Development of a Language Identification Tool capable of distinguishing between several languages and particularly between language varieties. Development of a web scraper to extract sentence pairs from the web in order to train machine translation models.
I was supervised by the CTO of Unbabel, João Graça, Ph.D.



Research Assistant


Development of low-resource solutions for Automatic Post-Editing of Machine Translations. It set the stage for a publication at ACL 2019.



### Proficient (Tools)
- Python
- PyTorch
- PyTorch Lightning
- HuggingFace's Transformers
- Weights & Biases and TensorBoard
- Git
- NumPy
- LaTeX
- Matplotlib

### I've also used
- Tensorflow
- Scikit-learn
- Pandas
- Bash and Shell Scripting

### Knowledge
- Machine Learning and Statistics
- Numerical/Statistical Programming
- Natural Language Processing
- Deep Learning
- Neural Networks for NLP
- Transformers and Pre-trained Language Models
- Natural Language Generation
- Generative and Latent Variable Models
- Weakly and Semi-Supervised Learning


Summer School Monitor


I was a monitor on the 2018 edition of the Lisbon Machine Learning School. Besides helping out in the day-to-day organization of the school, I was also responsible of answering questions and helping out students during the Lab sessions.


Instructor of Text Classification Specialization


During July 2018, Catarina Silva, Pedro Ferreira and I were responsible for the 4th Specialization of the Lisbon Data Science Starters Academy, releasing 3 Learning Units and organizing an hackaton related to the topic of Text Classification. Here's the links for the Learning Notebooks:

- [Feature Extraction](https://github.com/LDSSA/batch2-blu07)
- [Modelling](https://github.com/LDSSA/batch2-blu08)
- [Information Extraction and Advanced Text Classification Techniques](https://github.com/LDSSA/batch2-blu09)
- [Hackathon on Intent Classification](https://github.com/LDSSA/batch2-hackathon4)



I was a monitor on the 2019 edition of the Lisbon Machine Learning School. Besides helping out in the day-to-day organization of the school, I was also responsible of answering questions and helping out students during the Lab sessions.


Teaching Assistant in Deep Structured Learning


As a TA, I helped to grade and create the homeworks of the PhD course [Deep Structured Learning](https://andre-martins.github.io/pages/deep-structured-learning-ist-fall-2019.html). I also gave one of the lectures — [the PyTorch Tutorial](https://github.com/goncalomcorreia/pytorch-lecture)!


Publications

TitleA Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

ConferenceIn Proceedings of ACL, 2019

TitleUnbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing

ConferenceIn Proceedings of WMT, 2019

TitleAdaptively Sparse Transformers

ConferenceIn Proceedings of EMNLP, 2019

TitleEfficient Marginalization of Discrete and Structured Latent Variables via Sparsity

ConferenceIn Proceedings of NeurIPS, 2020