Hugo Sousa

NLP Researcher | Applied Scientist @ Amazon

News

Temporal Classifier paper was accepted at SIGIR'26
Defended my PhD thesis.
Temporal Game paper was accepted at CIKM'25
Joined Amazon as an Applied Scientist
Two papers accepted at AAAI'25
Event-based search paper was accepted at WSDM'25

Hi, thanks for visiting. I am an NLP Researcher and Applied Scientist at Amazon with a Ph.D. in Computer Science. My work bridges the gap between scientific research and real-world product engineering, focusing specifically on enhancing the reasoning capabilities and alignment of language models. The rest of the website lists some of my professional achievements. In short, I have publications in top-tier venues like AAAI and SIGIR and have worked with excellent researchers. Feel free to reach out. My email is at the bottom of the page.

Things I've Built

Tradutor

Fine-tune a language model to translate from English to European Portuguese.

code | model | app

tieval

A framework for evaluation of temporal information extraction systems.

code

Physio

A conversational AI agent to help with physical rehabilitation.

code

TEI2GO

Fast temporal expression identification systems.

code | models

more things that I've built can be found on my github and huggingface

Publications

Looking for the Bottleneck in Fine-grained Temporal Relation Classification

Hugo Sousa, Ricardo Campos, Alípio Jorge

SIGIR, 20-24 July 2026, Melbourne, Australia

preprint

The Temporal Game: A New Perspective on Temporal Relation Extraction

Hugo Sousa, Ricardo Campos, Alípio Jorge

CIKM, November 10-14, 2025, Seoul, Korea

paper | poster

Tradutor: Building a Variety Specific Translation Model

Hugo Sousa, Satya Almasian, Ricardo Campos, Alípio Jorge

AAAI, February 25 - March 4, 2025, Philadelphia, Pennsylvania, USA

paper | poster

Enhancing Portuguese Variety Identification with Cross-Domain Approaches

Hugo Sousa, Rúben Almeida, Purificação Silvano, Inês Cantante, Ricardo Campos, Alípio Jorge

AAAI, February 25 - March 4, 2025, Philadelphia, Pennsylvania, USA

paper | poster

Don't Forget This: Augmenting Results with Event-Aware Search

Hugo Sousa, Austin Ward, Omar Alonso

WSDM, 10-14 March 2025, Hannover, Germany

paper | poster

Text2Story Lusa: A Dataset for Narrative Analysis in European Portuguese News Articles

Sousa, H., Almeida, R., Silvano, P., Cantante, I., Campos, R., Jorge, A., Amorim, E., Leal, A., and Campos, R.

LREC-COLING, 20-25 May 2024, Torino, Italy

paper

Physio: An LLM-Based Physiotherapy Advisor

Rúben Almeida, Hugo Sousa, Luís Cunha, Nuno Guimarães, Alípio Jorge, and Ricardo Campos

🏆 Best Demo Paper 🏆 ECIR, 24-28 March 2024, Glasgow, Scotland

paper

GPT Struct Me: Probing GPT Models on Narrative Entity Extraction

Hugo Sousa, Nuno Guimarães, Alípio Jorge, and Ricardo Campos

WI-IAT, 26-29 October 2023, Venice, Italy

paper | code

TEI2GO: A Multilingual Approach for Fast Temporal Expression Identification

Hugo Sousa, Alípio Jorge, Ricardo Campos, and Ricardo Campos

CIKM, 21-25 October 2023, Birmingham, United Kingdom

paper | code

tieval: An Evaluation Framework for Temporal Information Extraction Systems

Hugo Sousa, Alípio Jorge, and Ricardo Campos

SIGIR, 23-27 July 2023, Taipei, Taiwan

paper | code

full list of publications here

Talks

Principles for Developing Machine Learning Projects

Presented for master students in AI at the University of Porto

December 2025

Work

Applied Scientist: @ Amazon
June 2025 to …
Teaching Assistant: @ University Porto
February 2023 to …
Applied Scientist Intern: @ Amazon
June 2024 to September 2024
Visting PhD Student: @ Carnegie Mellon University
October 2023 to December 2023
PhD Student: @ University Porto
December 2020 to December 2025;
Research Assistant: @ INESC TEC
December 2020 to June 2025;
Data Scientist: @ BNP Paribas
December 2019 to December 2020
Data Scientist: @ JTA: The Data Scientists
July 2018 to April 2019

Education

2020-2025: PhD, Computer Science; University of Porto
As an FCT Grant holder and part of the Text2Story project. Advised by Professor Alípio Jorge and Professor Ricardo Campos.
2017-2019: MS, Applied Mathematics; University of Porto
Thesis title: ECG Compression and QRS Detection: an IoT Approach
2014-2017: BSc, Physics; University of Porto

Other

🥉 Sword AI Challenge 15-23 July 2023
Member of the team - Team Physio - that took 3º place on Sword AI Challenge 2023.

IACT’23 @SIGIR 27 July 2023
Web and Dissemination Chair of the IACT Workshop.

Text2Story'23 @ECIR 2 April 2023
Web and Dissemination Chair of the Text2Story Workshop.

ESSIR 2022 18-22 July 2022
Attended the European Summer School in Information Retrieval.

Text2Story'22 @ECIR 10 April 2022
Web and Dissemination Chair of the Text2Story Workshop.

🥇 GENTIL Project 2021
Part of the team that developed the natural language processing pipeline for the GENTIL porject. This project was recognized as the "Best Future of Work Project" on Portugal Digital Awards 2021.

DSAA21 6-9 October 2021
Volunteer.

DESIRES 2021 15-18 September 2021
Went to the beautiful city of Padua to participate on the DESIRES 2021 conference.

LxMLS 2021 7-15 July 2021
Attended the Lisbon Summer School 2021.

Eurekathon 2020 5-7 November 2020
Member of the team - Feeding the Future - that took 2º place on Eurekathon 2020.

Contact

Feel free to reach out to me on LinkedIn or mail me at hmosousa [at] gmail [dot] com.

I keep track of the books I've read and I'm reading on Goodreads. Feel free to have a look and make any suggestions.