Gonçalo Raposo
From HLT@INESC-ID
Gonçalo Raposo is a dedicated researcher and Ph.D. candidate in Computer Science, specializing in Natural Language Generation. With a strong academic background in Aerospace Engineering, Gonçalo's passion for AI and deep learning led him to pursue a career in academia.
Currently, Gonçalo holds a position as an AI Research Scientist at Unbabel, a company that utilizes deep learning for translation and quality estimation. In this role, he contributes to the development of an innovative app called Halo, which aims to restore the voice of ALS patients. Gonçalo's work on Halo has garnered media attention and has opened up collaborations with real patients, further highlighting his commitment to impactful research.
Prior to his current position, Gonçalo gained valuable research experience as a visiting researcher at Carnegie Mellon University and as a researcher at INESC-ID. His research focus has been on Natural Language Processing, and he has made significant contributions to the field. His research projects have resulted in multiple publications in prestigious conferences such as SIGDIAL, ECIR, and ICASSP, where he has showcased his expertise in NLP and deep learning techniques.
In addition to his academic achievements, Gonçalo has been recognized for his outstanding performance as a student. He has been awarded a Gulbenkian merit scholarship for five years, as well as the ULisboa merit scholarship twice. These accomplishments not only reflect his intellectual capabilities but also demonstrate his dedication and commitment to his research endeavors.
Gonçalo's technical skills are well-rounded, with proficiency in languages such as C, C++, Python, and Matlab. He is also well-versed in using tools and technologies commonly employed in academia, including Git, PyTorch, and Unix/Linux. Moreover, he has experience in simulation tools like Simulink and has worked with Arduino and Raspberry Pi, showcasing his versatility and adaptability in utilizing different resources for research.
Beyond his academic and technical expertise, Gonçalo possesses a strong command of languages, including Portuguese, English, Spanish, and Chinese (HSK 2 level). This language proficiency has enabled him to effectively communicate and collaborate with researchers from diverse backgrounds, further enriching his research experiences.
In summary, Gonçalo Raposo is a dedicated and accomplished academic researcher in the field of Natural Language Generation. His passion for AI, deep learning, and NLP has driven him to excel academically and professionally, resulting in significant contributions to the field. With his strong research background, technical skills, and commitment to innovation, Gonçalo is poised to make meaningful contributions to the advancement of Natural Language Generation and further enrich the academic landscape in the field of Computer Science.
Artificial General Intelligence, Information Retrieval, Natural Language Processing, and Text Generation
Total Publications: 5
In Proceedings (Author)
- Information retrieval using fuzzy fingerprints
Gonçalo Raposo, Joao P. Carvalho, Luísa Coheur, Bruno Martins,
Information Processing and Management of Uncertainty in Knowledge-Based Systems, LNNS, Springer Nature, vol. 1174, pages 99–112, July 2024 - Prompting, Retrieval, Training: An exploration of different approaches for task-oriented dialogue generation
Gonçalo Raposo, Luísa Coheur, Bruno Martins,
Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue, Association for Computational Linguistics, pages 400--412, Prague, Czechia, September 2023 - Question rewriting? Assessing its importance for conversational question answering
Gonçalo Raposo, Rui Orlando Magalhães Ribeiro, Bruno Martins, Luísa Coheur,
European Conference on Information Retrieval, December 2022 - PositNN: Training Deep Neural Networks with Mixed Low-Precision Posit
Gonçalo Raposo, Pedro Tomás, Nuno Roma,
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2021), IEEE, IEEE, June 2021
Thesis (Author)
- Deep Learning with aproximate Computing: an energy efficient approach
Gonçalo Raposo, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal, Thesis, January 2021
Total Projects: 1
National Projects
- CRAI - Center for Responsible AI
Unbabel, IAPMEI, Societal Digital Transformation, 2023-01-01 - 2025-12-31