Osnabrück University

Research Unit Data Science

Osnabrück University navigation and search

Main content

Top content

An der Universität Osnabrück werden jedes Semester unterschiedlichste Lehrveranstaltungen aus dem Bereich Data Science angeboten. Die konkrete Ausrichtung und Schwerpunktsetzung der Veranstaltung liegt in den Händen der jeweiligen Vortragenden und ist natürlich auch vom Studiengang abhängig, für den sie angeboten wird.

So sind zum Beispiel die von den Arbeitsgruppen Cognitive Science, Informatik, Ökonometrie, Psychologie, Sozialforschung und angebotenen Veranstaltungen im Bereiche Data Science im Allgemeinen eher anwendungsorientiert, während die Angebote am Institut für Mathematik tendenziell eher theoretische Schwerpunkte setzen.

Current Term

Advanced NLP

Block course



The course will provide a historical perspective on deep learning for natural language processing (NLP) and will address recent topics such as Transformers (e.g., BERT and GPT), attention-based models and recent models for dialogue. In addition, we will discuss language acquisition, the cognitive plausibility of AI models, and the extraction of semantic structure from raw text. We will take a look at the current revival of linguistic structure in the deep learning community, either through the analysis of attention patterns in Transformers (according to which linguistic structure is a 'by-product' of neural attention) or through diagnostic classifiers.

We will go through a bit of theory in the first part of every lecture, and proceed with a discussion of
recent literature in the second part, with an active role for students which will introduce papers on the collective reading list and work in groups on short practicals.

Course objectives:
Students will obtain knowledge about the historical and current trends in deep learning-based NLP. They will be able to take a critical look at current literature and will have a rather advanced understanding of the challenges, opportunities and pitfalls of deep learning applied to language. Furthermore, they will have obtained practical knowledge about how to instantiate some of the latest NLP models.

Prerequisites: Basic programming; Deep Learning for NLP or other deep learning background.

Weitere Angaben

Ort: 93/E31
Zeiten: Termine am Montag, 25.03.2024 14:00 - 17:00, Dienstag, 26.03.2024 09:00 - 12:00, Dienstag, 26.03.2024 13:00 - 16:00, Mittwoch, 27.03.2024 09:00 - 12:00, Mittwoch, 27.03.2024 13:00 - 16:00, Donnerstag, 28.03.2024 09:00 - 12:00
Erster Termin: Montag, 25.03.2024 14:00 - 17:00, Ort: 93/E31
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)


  • Cognitive Science > Bachelor-Programm
  • Cognitive Science > Master-Programm
  • Cognitive Science > Promotionsprogramm