Main content
Top content
The Osnabrück University offers every Semester a wide variety of courses in the field of Data Science. The specific orientation and focus of the course is in the hands of the responsible lecturer and of course also depends on the degree programme for which it is offered.
For example, the courses offered by Cognitive Science, Computer Science, Econometrics, Psychology, Social Research and working groups in the field of Data Science are generally more application-oriented, while the courses offered at the Institute of Mathematics tend to have a more theoretical focus.
Current term
Advanced NLP
Block course
8.3546
Dozenten
Beschreibung
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: nicht angegeben
Zeiten: Termine am Montag, 31.03.2025 14:00 - 17:00, Dienstag, 01.04.2025 09:00 - 12:00, Dienstag, 01.04.2025 13:00 - 16:00, Mittwoch, 02.04.2025 09:00 - 12:00, Mittwoch, 02.04.2025 13:00 - 16:00, Donnerstag, 03.04.2025 09:00 - 12:00, Donnerstag, 03.04.2025 13:00 - 16:00
Erster Termin: Montag, 31.03.2025 14:00 - 17:00
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)
Studienbereiche
- Cognitive Science > Bachelor-Programm
- Cognitive Science > Master-Programm
- Cognitive Science > Promotionsprogramm
