Seminar: Seminar Natural Language Understanding (Master) - Details

Seminar: Seminar Natural Language Understanding (Master) - Details

Close message box
You are not logged into Stud.IP.

General information

Course name Seminar: Seminar Natural Language Understanding (Master)
Course number INF-0468
Semester SS 2024
Current number of participants 3
Home institute Professur für Sprachverstehen mit Anwendung Digital Humanities
Courses type Seminar in category Teaching
First date Tuesday, 16.04.2024 17:30 - 19:00, Room: (1054 N)
Veranstaltung findet in Präsenz statt / hat Präsenz-Bestandteile Yes
Hauptunterrichtssprache deutsch
Weitere Unterrichtssprache(n) englisch
ECTS points 4

Rooms and times

(1054 N, self study)
Tuesday: 17:30 - 19:00, weekly (8x)
(1054 N)
Tuesday: 17:30 - 19:00, weekly (3x)
(D2127)
Tuesday: 17:30 - 19:00, weekly (2x)

Module assignments

Comment/Description

Recently, large language model based applications such as ChatGPT have achieved new levels of performance on various natural language understanding tasks. At the same time, they suffer from problems such as bias and hallucination. In this seminar, we will discuss recent state-of-the-art approaches to computational semantics and (automatic) natural language understanding. Prior participation in the "Introduction to Natural Language Processing" course is certainly a plus, but not a hard requirement. Prior knowledge in machine learning will be helpful.

In the summer semester 2024, this seminar will be taught jointly with the Department of Philology and History to foster interdisciplinary collaboration with students of linguistics / language studies. See course: https://digicampus.uni-augsburg.de/dispatch.php/course/overview?cid=7dddb97d5058d9b13a81ee167ef8ed6b

At the beginning of the semester, we will offer several sessions providing guidance on the technical background, on how to read scientific papers effectively, on how to structure your presentation, and on how to write your term paper.

Registration mode

The enrolment is binding, participants cannot unsubscribe themselves.