Scholar
Lachlan McPheat
Google Scholar ID: wDpWotwAAAAJ
The Alan turing Institute
Citations & Impact
Citations
34
H-index
5
i10-index
0
Publications
10
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - An Empirical Study of Conformal Prediction in LLM with ASP Scaffolds for Robust Reasoning (with Navdeep Kaur, Alessandra Russo, Anthony G. Cohn, and Pranava Madhyastha)
- - Donkey Sentences Via DisCoCat (with Daphne Wang)
- - A Quantum Natural Language Processing Approach to Pronoun Resolution (with Hadi Wazni, Kin Ian Lo, and Mehrnoosh Sadrzadeh)
- - Vector Space Semantics for Lambek Calculus with Soft Subexponentials (with Mehrnoosh Sadrzadeh and Hadi Wazni)
- - Anaphora and Ellipsis in Lambek Calculus with a Relevant Modality: Syntax and Semantics (with Mehrnoosh Sadrzadeh, Adrian Correia, and Alexi Toumi)
- - Categorical Vector Space Semantics for Lambek Calculus with a Relevant Modality (with Mehrnoosh Sadrzadeh, Hadi Wazni, and Gijs Wijnholds)
- - Awards:
- - Best Presentation Award at the LGBTQ+STEM Conference 2022.
Research Experience
- - From August 2024, a research associate at The Alan Turing Institute, working on Robust Inference with Probabilistic Answer Set Programs Scaffolds for Large Language Models.
- - Visited Bekki Lab at Ochanomizu University in Tokyo from May to August 2024, studying Bekki's Dependent Type Semantics of natural language.
- - Interned at Quantinuum's Oxford office from June to September 2022, working under Bob Coecke in graphical Discourse Representation Theory.
Education
- Completed PhD at PPLV, UCL Computer Science, supervised by Mehrnoosh Sadrzadeh.
Background
- Research interests include Transparency and Interpretability in AI/ML, Computational Linguistics, NLP, Distributional-Compositional Semantics, Categorical Semantics, Category Theory, and Dependent Type Theory. Focuses on methods of modelling referential phenomena in natural language using distributional-compositional semantics.
