About me
I am an Assistant Professor at the School of Computing and Communications, Lancaster University, where I work with the UCREL NLP Group, the Data Science Institute, and Security Lancaster.
My research focuses on developing Machine Learning (ML) approaches for Natural Language Processing (NLP), with a particular emphasis on NLP for Social Good. My work spans three main research themes:
Enhanced Communication: I am interested in developing NLP technologies that improve both human-human communication and human-AI interaction. For human-human communication, my research includes areas such as machine translation, text summarisation, text simplification, and related technologies that make information more accessible across languages and communities. For human-AI interaction, I am interested in understanding and improving how people interact with language technologies, including areas such as machine translation quality estimation and methods for assessing the reliability and usefulness of model-generated outputs.
Security and Safety: I develop NLP and Machine Learning methods for improving online safety and understanding potentially harmful content. My research in this area includes offensive language and hate speech detection, misinformation detection, and the analysis of language related to mental health.
Digital Humanities: I am also interested in applying NLP techniques to problems in the Digital Humanities and related interdisciplinary domains. My work has included applications in legal NLP, historical text analysis, and education.
Across all three areas, I have a particular interest in low-resource languages, explainable Machine Learning, and the development of open-access datasets, benchmarks, and models that can support wider research and real-world applications.
