Gustavo Penha

I am a researcher in the field of information retrieval, interested in machine learning, ranking models, recommender systems, and natural language processing. I am currently at the fourth year of my PhD at TU Delft on the topic of conversational search and recommendation, under the supervision of Claudia Hauff.
I have BSc and MSc degrees from the department of Computer Science of UFMG, where I was supervised by Rodrygo Santos. I worked as a data scientist for 3 years in Hekima, which was later bought by iFood to boost their AI talent base.
I am also passionate about photography. I am working on my first photobook, if you are curious check some photos here ๐ผ๏ธ.
news
Jun 6, 2022 | Internship planned for the summer of 2022 at Spotify research ๐ต. |
---|---|
Apr 19, 2022 | We won the best paper award with our ECIRโ22 paper ๐ ๐. |
Aug 27, 2021 | Finished my research internship at Amazon ๐ฆ: CHIโ22 & CHIIRโ22. |
research interests
Representation learning for rankingText encoders learn representations for queries and documents, which are then used to calculate a relevance score. The goal is that relevant documents get close to the query and non-relevant documents get far from the query in the embedding space. I am interested in many aspects of representation learning, including negative sampling, disentanglement and interpretability. |
|
Explainability and model understandingInformation filtering systems, such as document rankers and recommender systems, have a large impact into what we are able to find, what we are exposed to and the decisions we make. Understanding the behavior of such models, when they fail and how robust they are is crucial for both machine learning practitioners and end users. |
selected publications
presentations
Slides for our ECIR 2022 paper on query variations. video ๐ฌ.Slides for the Glasgow IR seminar on 10 May 2021: video ๐ฌ.