Seminar Natural Language Processing

This seminar offers a conceptual and practical introduction into modern Natural Language Processing (NLP). The course is structured around a series of lectures, each centered on a seminal publication and featuring presentations by academic guest speakers. The covered NLP techniques include the latest advancements such as transformer architectures, BERT, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), alongside foundational methods like Bag-of-Words (BoW), TF-IDF, word2vec, and LSTM.

Prior to each session, students are required to read a designated research paper and prepare a critical question for discussion. This engagement will deepen understanding and foster analytical skills. Additionally, each participant will undertake a personal project in the realm of NLP, culminating in a final presentation that demonstrates their applied knowledge and insights. This seminar is mandatory for all students conducting a bachelor or master thesis at the Research Center for Digital Sustainability.

Details

Code 61611
Type Seminar
ECTS 5
Site Bern
Track(s) T6 – Data Science
Semester A2024

Teaching

Learning Outcomes

Upon successful completion of this course, you will …
… have developed your presentation skills
… have planned, executed and presented a project in the field of NLP … know the most important methods of NLP
… be able to understand papers in the field of NLP
… be able to understand and critically comment on presentations of your fellow students

Lecturer(s) Matthias Stürmer
Language english
Course Page

The course page in ILIAS can be found at https://ilias.unibe.ch/goto_ilias3_unibe_crs_3102245.html.

Schedules and Rooms

Period Weekly
Schedule Friday, 10:15 - 12:00
Location UniBE, Hauptgebäude H4
Room 105

Evaluation

Evaluation type continuous evaluation

Additional information

Comment

First Lecture
The first lecture will be announced later.