136040 VU Practical Machine Learning for Natural Language Processing (2023S)
10.00 ECTS (4.00 SWS), SPL 13 - Finno-Ugristik, Nederlandistik, Skandinavistik und Vergl.Literaturw.
Continuous assessment of course work
Labels
MIXED
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).
- Registration is open from Mo 06.02.2023 08:00 to Mo 27.02.2023 08:00
- Deregistration possible until Fr 31.03.2023 23:59
Details
max. 25 participants
Language: English
Lecturers
Classes (iCal) - next class is marked with N
Thursday
02.03.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
07.03.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
09.03.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
14.03.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
16.03.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
21.03.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
23.03.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
28.03.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
30.03.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
18.04.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
20.04.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
25.04.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
27.04.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
02.05.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
04.05.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
09.05.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
11.05.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
16.05.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
23.05.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
25.05.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
01.06.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
06.06.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
13.06.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
15.06.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
20.06.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
22.06.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Tuesday
27.06.
09:45 - 11:15
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Thursday
29.06.
11:30 - 13:00
Seminarraum 6 Hauptgebäude, Tiefparterre Stiege 9 Hof 5
Information
Aims, contents and method of the course
In this lecture, basic 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 using the perceptron algorithm to word vectors and simple neural networks. Basic knowledge of Python or the willingness to acquire it quickly is assumed (the basic control and data structures, such as class definitions or dictionaries). The language of the lecture is German or English (depending on the lecturer).
Assessment and permitted materials
There will be regular assignments during the semester and a written exam at the end.
Minimum requirements and assessment criteria
Regularly working on assignments during the semester and achieving a minimum number of points in an exam.
Examination topics
Knowledge of the algorithms and machine learning methods discussed in the lecture, as well as their application and implementation discussed 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/“Keras Developer Guides”
https://keras.io/guides/
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/“Keras Developer Guides”
https://keras.io/guides/
Association in the course directory
S-DH (Cluster I: Language and Literature)
Last modified: Tu 14.02.2023 12:08