Affiliated with the Language Technology Group (LT), Department of Informatics, University of Hamburg
Researches all aspects of natural language processing technologies and applies them in practice
Focuses on unsupervised, large-scale methods for natural language semantics
Studies statistical semantics by computing semantic similarities and relations between lexical items from large text corpora, applied in semantic indexing, paraphrasing, and lexical chain identification
Emphasizes unsupervised and knowledge-free methods such as lexical graph clustering, topic models, and neural representations to discover structures in large text collections for use in supervised machine learning