I am a UK-based faculty member in Computer Science at Manchester Metropolitan University, specialising in Natural Language Processing. My research addresses how models can be transferred to domains where labelled data is scarce and source language differs substantially from general-purpose corpora, a problem that arises directly when applying NLP to biodiversity text such as scientific literature, historical archives, and policy documents. I am interested in joining a BiodivFuture consortium where this research agenda can support evidence synthesis on novel ecosystems.

Skills / keywords (concrete capabilities):
Unsupervised and self-adaptive domain adaptation
Information and relation extraction from unstructured text
Learning from noisy, multi-annotator, or weakly labelled data
Transformer-based and LLM-based classification
Multilingual NLP and annotation bias analysis
Python, PyTorch, Hugging Face

Keywords: Domain Adaptation; Information Extraction; Weak Supervision; Biodiversity NLP

Bioinformatics
Languages and literature
Mental Health

I am a UK-based faculty member in Computer Science at Manchester Metropolitan University, working on domain adaptation and information extraction. I see a natural fit with projects under Theme A that need to extract ecological interactions, species associations, or functional traits from heterogeneous text sources. Many consortiums have the ecological expertise but lack the NLP capacity to mine unstructured literature, historical archives, or monitoring reports for fragmented knowledge about emerging communities.

nlp, llm, information extraction, domain adaptation

Happy to have joint publications in A/A* in NLP/AI, or co-located domain-specific workshop like Ecology, Environment, and Natural Language Processing (NLP4Ecology).
Has a paper to be present in EMNLP 2026 on information extraction in Nov.