Forschungsstelle Digitale Nachhaltigkeit

Seminar on Natural Language Processing (NLP)

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.

Before each lecture, the students have to read the indicated research article and ask a key question for the discussion. In addition, each student has to conduct and eventually present a personal project related to NLP. This seminar is mandatory for all students conducting a bachelor or master thesis at the Research Center for Digital Sustainability.

Time, Location, and Links

Schedule 2021

Date Topic Guest Speaker
24 September 2021 Overview and introduction Patrizio Collovà, Bern University of Applied Sciences
1 October 2021 Bag-of-words (BoW) and term frequency–inverse document frequency (TF-IDF) Dominic Schweizer, University of Bern
8 October 2021 NRP77 project on reidentification of Swiss judgements Joel Niklaus and Matthias Stürmer, University of Bern
15 October 2021 Presentation of student projects  
22 October 2021 word2vec Prof. Tobias Hodel, Digital Humanities University of Bern
27 Oktober 2021 Long short-term memory (LSTM) Mathias Müller, PhD student at University of Zürich
5 November 2021 Hands-on session  
12 November 2021 Latent Dirichlet allocation (LDA) Silvia Terragni, PhD student at University of Milano-Bicocca
19 November 2021 Transformers  
26 November 2021 BERT Ilias Chalkidis, NLP Postdoctoral Researcher at University of Copenhagen
3 December 2021 GPT3  
10 December 2021 Student presentations  
17 December 2021 Student presentations  
24 December 2021 no lecture