|
Root number
|
475403 |
Semester
|
HS2024 |
Type of course
|
Colloquium |
Allocation to subject
|
Digital Humanities |
Type of exam
|
Presentation |
Title |
Applications of Natural Language Processing for the Humanities |
Description |
Natural Language Processing is the digital treatment of textual documents. Language models (from large language models such as GPT4 to smaller custom-made models) are currently shaping the landscape of NLP. In the course, we will focus on the basics and introduce the participants to an in-depth understanding of the concepts of NLP.
Based on examples from the Digital Humanities of the University of Bern, the participants will explore current implementations' capabilities and shortcomings, from Word2Vec to character-based and transformer language models. Finally, we will discuss how LLMs change the scene and ask for new strategies to deal with NLP tasks.
We will use FlairNLP (Python-based) as the framework of choice for most of the tasks. As a hub for models, we rely on huggingface. |
ILIAS-Link (Learning resource for course)
|
Registrations are transmitted from CTS to (no admission in ILIAS possible).
ILIAS
|
Link to another web site
|
|
Lecturers |
Prof. Dr.
Tobias Mathias Hodel, Walter Benjamin Kolleg (WBKolleg) ✉
|
ECTS
|
3 |
Recognition as optional course possible
|
Yes |
Grading
|
passed/failed |
|
Dates |
Tuesday 14:15-16:00 Weekly
|
|
Rooms |
Seminarraum F -123, Hörraumgebäude Unitobler
|
|
Students please consult the detailed view for complete information on dates, rooms and planned podcasts. |