Portrait of Johannes Bjerva

Linguistic structure · Multilingual NLP · Security and privacy

Johannes Bjerva

Professor of Natural Language Processing · Group Leader

I study how the structure and diversity of language can help us build AI systems that are more capable, secure, private, and trustworthy.

Johannes leads AAU NLP and is Head of the Copenhagen Section of Aalborg University’s Department of Computer Science. His research programme combines multilingual NLP, linguistic typology, formal and semantic perspectives, and language-model security. The unifying question is how knowledge about language can reveal model behaviour and support language technologies that remain reliable across languages and contexts.

Linguistically grounded NLP

Using typology, semantics, and cross-lingual structure to understand how models learn and generalise across languages.

Language-model security

Studying memorisation, inversion, poisoning, and other threats through a multilingual and linguistically informed lens.

Trustworthy language technology

Connecting fundamental NLP to factuality, education, privacy, safety, and reliable deployment in real-world settings.

Selected programmes

Projects and labs

LM²-SECTRUSTAI:SECURITYFormal Semantic Methods for AI SafetyMultilingual Modelling for Resource-Poor Languages

Selected work

5 representative papers

Supervision and collaboration

Questions worth working on

I welcome research questions that take language seriously and connect strong empirical work with linguistics, semantics, security, privacy, or adjacent areas where NLP can make a genuine contribution.