top of page

I am a 3rd year PhD student funded by the Wellcome Trust Neural Dynamics programme at the University of Bristol. My research interests span computational cognitive neuroscience, natural language processing and the intersection of deep learning and neuroscience. 

 

I work with Nina Kazanina (NeuroLingo) and Conor Houghton (CNU). I have worked on projects in natural language processing, episodic memory and reward learning. I am interested in using methods ranging from cognitive tasks, computational modelling, deep learning and EEG.

I have also spent time teaching and in various committee roles at the university. 

SCIENCE

PROJECTS

Few-Shot Learning in Language Models

LSTM language models successfully learn the grammatical gender of novel nouns in a few-shot learning paradigm, and apply this knowledge in a previously unseen context, suggesting that they are capable of abstract syntactic generalisation and represent grammatical gender as a context-invariant property, similar to humans.
EACL 2024 Paper

ACL 2023 (RepL4NLP) Poster

Large Language Models and Psycholinguistics 
Large Language models are not intended as models of human linguistic processing. They are, however, very successful at providing a model for language. Large language models are important in psycholinguistics: they are useful as a practical tool, as an illustrative comparative, and philosophically, as a basis for recasting the relationship between language and thought. Our Commentary on Bowers et al. 2023.

Grammatical Generalisation in Language Models 
Deep neural networks (DNNs) are surprisingly great at learning language rules required for natural language modelling.  Do LSTMs really learn abstract grammatical rules like humans, or do they rely on simple heuristics? We use gender agreement to study the mechanisms behind LSTMs' linguistic abilities. Contributing to the debate on how humans vs. machines process language.

EMNLP 2022 (BlackboxNLP) Paper

NMC22 Talk

Adaptive Memory & Reward

The brain preferentially remembers particularly meaningful events. However, we cannot know whether an event is meaningful when we encounter it, thus we need an adaptive memory system that enhances the memory of events after or before it becomes salient. We explore whether such a system is driven by reward. 

Scientific Reports Paper

FENS22 Poster

TEACHING

3_edited.jpg

Graduate Lecturer 

Understand Global Issues using Data 
Developed teaching material and delivered workshops on statistics, data analytics and visualisation. Course

Teaching Assistant

Foundations of Psychology Course

Demonstrator

Undergraduate Physiology Labs

ROLES

Postgraduate Student Representative

Responsible for organising community-building and wellbeing activities, and representing the student voice at faculty and university level meetings. 

EDIC Committee Representative 

Represented student voice during committee meetings and contributed to Athena Swan action plan for gender equality.

Link

Neural Dynamics Forum 

Organised seminars on integrating experimental and computational approaches in neuroscience. 

Link

bottom of page