Universität Wien

136040 VU Practical Machine Learning for Natural Language Processing (2024S)

10.00 ECTS (4.00 SWS), SPL 13 - Finno-Ugristik, Nederlandistik, Skandinavistik und Vergl.Literaturw.
Continuous assessment of course work
Moodle
Th 23.05. 11:30-13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 25 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

Tuesday 05.03. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 07.03. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 14.03. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 19.03. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 21.03. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 09.04. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 11.04. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 16.04. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 18.04. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 23.04. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 25.04. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 30.04. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 02.05. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 07.05. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 14.05. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 16.05. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 21.05. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 28.05. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 04.06. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 06.06. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 11.06. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 13.06. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 18.06. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 20.06. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday 25.06. 09:45 - 11:15 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday 27.06. 11:30 - 13:00 Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5

Information

Aims, contents and method of the course

In this lecture, fundamental machine learning algorithms are implemented in Python and applied to natural language processing problems. The focus is on vector representations of texts, and the methods range from text classification with the perceptron algorithm, to word vectors, to simple neural networks.
Basic knowledge of Python or the willingness to learn it quickly is required (basic control and data structures, such as class definitions or dictionaries). The language of the lecture is English.

Assessment and permitted materials

During the semester, participants will have to hand in programming exercises and moodle assignments. There will be a written final exam at the end of the semester.

Minimum requirements and assessment criteria

A weighted average of the points achievable from programming exercises (weight: 20%), Moodle assignments (weight: 20%) and written final exam (weight: 60%) is calculated. The course is passed with 50% or more of the maximally achievable weighted average of points.

Examination topics

Knowledge of the algorithms and machine learning methods covered in the lecture, as well as their application and implementation covered in the exercise.

Reading list

“Marc Pilgrim: Dive into Python”
https://diveintopython3.problemsolving.io/

“Hal Daume: A course in machine learning”
Kapitel 4,5,7,10
http://ciml.info/

“Goldberg & Levy: word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method”
https://arxiv.org/abs/1402.3722

“Christopher Olah’s blog”
http://colah.github.io/

“Goodfellow et al.: Deep Learning”
(advanced)
https://www.deeplearningbook.org/

Association in the course directory

S-DH Cluster I: Language and Literature

Last modified: Mo 04.03.2024 14:26