About Me
I am a Ph.D. student in the Department of Computer Science at the University of Manchester, as part of the Neuro-Symbolic AI Group. My research focuses on investigating AI models, such as Large Language Models (LLMs), to perform Natural Language Inference in the clinical domain, including tasks like retrieving and ranking clinical trials for patients and classifying clinical trial protocol deviations. A key aspect of my work is designing hybrid neuro-symbolic architectures that are both explainable, and integrated with ground knowledge, such as ontologies, for improved robustness, efficiency, and controllability. Additionally, working to uncover inference mechanisms and limitations of LLMs.
Education
University of Nottingham, 2020
MSc in Computer Science and Artificial Intelligence, with Distinction
Thesis: “Histological Image Registration using Deep Convolutional Features”
During my MSc, I developed a strong foundation in Artificial Intelligence, focusing on key areas such as convolutional neural networks. My dissertation work centered on applying AI to the clinical domain, which has been pivotal in shaping my research direction.
University of Leicester, 2019
BSc Hons in Mathematics, with First Class Honours
Thesis: “Convolutional Neural Networks for Audio Classification”
During my BSc, I honed my mathematical reasoning and problem-solving skills, which laid the groundwork for my transition into AI and computational research. My studies included a deep dive into algebra, calculus, and statistics, which have proven essential in my current research.
Papers
NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports
Co-authors: Mael Jullien, Marco Valentino, Hannah Frost, Paul O’Regan, Donal Landers, André Freitas.
In Proceedings of The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023).
Controlled LLM-based Reasoning for Clinical Trial Retrieval
Co-authors: Mael Jullien, Alex Bogatu, Harriet Unsworth, Andre Freitas
arXiv, 2024
Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language
Co-authors: Mael Jullien, Marco Valentino, André Freitas
arXiv, 2022
Competitions and Shared Tasks Organisation
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
Co-authors: Mael Jullien, Marco Valentino, André Freitas
The 18th International Workshop on Semantic Evaluation (Semeval-2024) co-located with the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024). Mexico City, Mexico.
SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data
Co-authors: Mael Jullien, Marco Valentino, André Freitas
The 17th International Workshop on Semantic Evaluation (Semeval-2023) co-located with The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). Toronto, Canada.
Talks and Posters
NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports
Poster presentation at the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023).
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
Oral presentation at the 18th International Workshop on Semantic Evaluation (Semeval-2024) co-located with the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024). Mexico City, Mexico.
SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data
Oral presentation at the 17th International Workshop on Semantic Evaluation (Semeval-2023) co-located with The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). Toronto, Canada.
AI-Enabled Monitoring of Clinical Trial Protocol Deviations
Oral presentation at the Advances in Data Science and Artificial Intelligence Conference 2024 (ADSAI 2024). Manchester, UK.
Awards
PhD Scholarship
University of Manchester
Awarded a PhD scholarship by the University of Manchester.
Best Task Paper Award Honorable Mention
SemEval-2023, ACL 2023
Received an Honorable Mention for the Best Task Paper at the 17th International Workshop on Semantic Evaluation (SemEval-2023), co-located with the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023).