About us
Lancaster University’s research on Natural Language Processing (NLP) connects with corpus and computational linguistics, digital humanities, text mining, and more widely in the social sciences and humanities, prioritising real-world applications in all domains where language is involved, e.g. cyber security, spatial narratives, historical sources, health communication, financial information environments, low-resource languages and multilingual contexts. NLP can help scale up manual qualitative analysis to extreme-scale quantitative analysis, while retaining explainability and accuracy.
We specialise in the creation, annotation, and analysis of multilingual language resources, including corpora (large collections of text or transcribed speech), lexicons and semantic taxonomies. We develop and evaluate NLP methods and software for semantic analysis, named entity recognition, machine translation, emotion, anaphora, sentiment and metaphor analysis, mis/disinformation, toxic language, simplification and summarisation, and NLP for social good.
We are mainly based in two world leading research centres: University Centre for Computer Corpus Research on Language (UCREL) and Centre for Corpus Approaches to Social Science (CASS), and we collaborate with other researchers in the Language Digital Humanities Centre, Forensic linguistics, Cyber security and Technology Research (FACTOR), and two University institutes: Data Science and AI (DSAIL) and Security Lancaster.
