
Vision & Research Focus
My research work deals with understanding and filling the gap between the realm of human though, and in particular human language and the realm of computer machinery, which is the key component the next generation of intelligent systems that will be able to automatically understand and process the meaning of information at scale.
I have been involved with Artificial Intelligence (AI) and Natural Language Processing work for over a decade, in which this field has seen several big advancements in technology and practical applications, from the generation and organization of massive textual corpora to Neural-based Machine Translation. Now, the application of AI in many areas hangs in the ability to explain the answers it provides, with the analysis of information from healthcare, energy and transportation sectors, and of the propagation of misinformation on online social media posing as challenging, but necessary testing grounds for the design of explainable AI, wherein lies my current efforts.
Profile
Danilo Carvalho is a Principal Clinical Informatician (Research Associate) for the Digital Cancer Research team at the National Biomarker Center of the University of Manchester, working on Safe and Explainable Artificial Intelligence (AI) architectures.
[About]
Current Research
◈ Theoretical research on verification and interpretability of neural AI architectures.
◈ Application of explainable AI systems into safety-critical tasks in healthcare.
◈ Applied research in the fields of Natural Language Processing, Knowledge Representation and Computer Vision on the analysis of biomedical data.
Areas of Interest
◈ General
- Computational Linguistics / Natural Language Processing
- Artificial Intelligence
- Data Science
- Software Engineering
◈ Specific (summary)
- Explainable AI
- Open Information Extraction
- Semantic Representation
- Patent / Bibliographical Databases
- Language Models
Events
Montague semantics and modifier consistency measurement in neural language models [Presentation at COLING 2025]
Formal Semantic Controls over Language Models [Tutorial at LREC-COLING 2024]
Latest Publications
- Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
- PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
- SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
- LangVAE and LangSpace: Building and Probing for Language Model VAEs (preprint)
Projects
LangVAE & LangSpace: Building and Probing for Language Model VAEs [more]
- Train and run Language Model Variational Autoencoders (LM-VAEs)
- Probing of sentence representations
SAF-Datasets: Dataset loading and annotation facilities for the Simple Annotation Framework [more]
- Easy access to Annotated NLP Datasets
- Multi-level annotations: document, sentence, token
TDV: Word vector representation based on Wiktionary meanings [more]
- Morpheme to phrase representation
- NLP features: Multi-language, sense polarity, sense disambiguation by POS
EasyESA: Easy Semantic Approximation with Explicit Semantic Analysis [more]
- Provides concept vectors and a semantic relatedness measure
- Query explanations can give insights on relatedness results