I am a Lecturer (≈ Assistant Professor) in Natural Language Processing at the University of Edinburgh, where I am part of the Institute for Language, Cognition, and Computation (ILCC), and an Affiliated Lecturer at the University of Cambridge.
If you are a prospective student, collaborator, or industry partner please visit the FAQ page for more information.
Previously, I was a visiting postdoctoral scholar at Stanford University and a postdoctoral fellow in computer science at Mila - Quebec AI Institute in Montreal. In 2021, I obtained a PhD in computational linguistics from the University of Cambridge, St John’s College. I interned as AI/ML researcher at Apple in Cupertino.
The main research foci of my lab are:
- modular deep learning [1]: designing neural architectures that route information to specialised, autonomous modules. This includes sparse adaptation for parameter-efficient fine-tuning [2], recombing skills for systematic generalisation [3, 4], and model merging [5].
- grounding: language learning and use in perception and action, taking into account the world’s cross-cultural diversity [6], integrating vision into language models [7], and probing LLMs for the temporal aspects of their internal world model;
- computational typology [8]: using computational tools to study the cross-lingual variation of the world’s languages scientifically [9, 10].
- multilingual natural language processing: developing language technology in a diverse range of languages, by finding the correct inductive biases for sample efficient learning [11] or jointly learning how to translate and classify / generate [12]; creating new annotated multilingual datasets [13, 14].
- tokenization-free language modelling: jointly performing input segmentation and self-supervised learning, by inducing hierarchical abstractions on top of raw inputs [15].
My research earned a Google Research Faculty Award. I received 2 Best Paper Awards at EMNLP 2021 and RepL4NLP 2019. I am a board member of SIGTYP, the ACL special interest group for computational typology, a scholar of the European Lab for Learning and Intelligent Systems (ELLIS), and part of the TACL journal editorial team. I am a scientific advisor for the AI company Ivado Labs.