NLP Seminar Spring 2022
This seminar provides a conceptual and practical introduction into modern Natural Language Processing (NLP) methods and technologies. Each lecture introduces a new NLP approach based on a seminal publication and including a presentation of an academic guest speaker. The NLP methods include Bag-of-words (BoW), term frequency–inverse document frequency (TF-IDF), word2vec, long short-term memory (LSTM), latent Dirichlet allocation (LDA), transformers, BERT, and GPT-3. The lectures have been recorded from the previous Semester and are (in most cases) available on BigBlueButton. Please find the schedule of the Seminar here, listing relevant research articles or blogposts.
Each student will conduct and present an individual project related to NLP. The topic descriptions can be found here. For maximum learning opportunities from other student's presentations, active participation is mandatory.
This seminar is mandatory for all students conducting a bachelor or master thesis at the Research Center for Digital Sustainability. They will present the progress of their theses in the seminar.
The Natural Language Processing Seminar will stop with this edition because of a lack of funding.
Time, Location, and Links
- Every Friday from 10:15h to 12:00h
- Seminar Room 105, Main Building H4, 3012 Bern
- Template Slide for Progess Report: https://docs.google.com/presentation/d/1NdaxR1CH34tKsD1ZVo3ZHp2wyg91X4oBzSlab_SIuyA/edit?usp=sharing
- Hybrid on BigBlueButton: https://bbb.ch-open.ch/b/joe-2kn-jun-aqw
- Telegram Chat: https://t.me/+cf5b8mOgWE4wOTI0
- ILIAS: https://ilias.unibe.ch/goto_ilias3_unibe_crs_2281872.html