Osnabrück University

Research Unit Data Science

Osnabrück University navigation and search

Deutsch

Submenu on the topic Teaching

Position indicator

You are here: Home > Teaching > Current Term

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

Robustness and generalisation in natural language processing

8.3564

Dozenten

Beschreibung

In natural language processing (NLP), we set out to solve language-related tasks (e.g., machine translation, question answering) but often evaluate on narrow, in-distribution test datasets. With recent advances in deep learning, modern systems have achieved high accuracy on many canonical datasets, but still seem far from solving general tasks. In this class, we will survey recent research on robustness and generalisation that studies this gap between in-distribution accuracy and task competency through out-of-distribution settings. We will learn about different settings in which NLP systems often fail to generalise well, including adversarial perturbations, settings that require compositional reasoning, and domain transfer. Across these topics, we will cover methods both for measuring these robustness and generalisation issues and ways that we can improve model robustness and generalisation.

Prerequisites
Familiarity with natural language processing and/or machine learning at the level of
8.3470 Deep learning for natural language processing (students enrolled to 8.3470 in this semester are also eligible). Please email me if you want to enrol but are unsure if you meet the prerequisites.

Weitere Angaben

Ort: 93/E31: Mo. 16:00 - 18:00 (12x), 66/E34: Di. 14:00 - 16:00 (13x)
Zeiten: Mo. 16:00 - 18:00 (wöchentlich), Ort: 93/E31, Di. 14:00 - 16:00 (wöchentlich), Ort: 66/E34
Erster Termin: Montag, 24.10.2022 16:00 - 18:00, Ort: 93/E31
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)

Studienbereiche

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

Footer