Universität Wien

052315 VU Natural Language Processing (2024W)

6.00 ECTS (4.00 SWS), SPL 5 - Informatik und Wirtschaftsinformatik
Continuous assessment of course work
Moodle
Mo 11.11. 11:30-14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG

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

  • Monday 07.10. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 14.10. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 21.10. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 04.11. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 18.11. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 25.11. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 02.12. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 09.12. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 16.12. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 13.01. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 20.01. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG
  • Monday 27.01. 11:30 - 14:45 PC-Unterrichtsraum 2, Währinger Straße 29 1.OG

Information

Aims, contents and method of the course

The students know the basics of natural language processing. They master the use of linguistic resources and tools, and are able to efficiently apply them to independently design and implement solutions for subject-specific problems. Students can convey this knowledge in written form and in oral presentations.

This is a practice-oriented course with a significant implementation requirement. It is based on the NLTK book with many implementation examples in Python.

This course covers the following topics: language processing and Python, accessing text corpora and lexical resources, processing raw text, writing structured programs, categorizing and tagging words, learning to classify text, extracting information from text, analyzing sentence structure, building feature based grammars, analyzing the meaning of sentences. The corresponding chapters from the NLTK book are made available as Jupyter Notebooks through Moodle.

The main software tools used in this course are Python 3, NLTK, and Jupyter Notebooks for submission and presentation of exercises.

Assessment and permitted materials

There is one written exam at the end of the course. The result accounts for 40 % of the total rating.

The remaining 60 % are earned through voluntary oral presentations during the semester. There are altogether 10 exercise sheets with problems to solve. For a certain exercise sheet at most one problem can be presented by a student. The best result for the first 4 exercise sheets accounts for 30 % of the total rating, the best result for the remaining 6 exercise sheets accounts for the final 30 %.

Minimum requirements and assessment criteria

A mandatory prerequisite for this course is the successful completion of Foundations of Data Analysis.

The exercise sheets are provided as Jupyter Notebooks through Moodle assignments and must be submitted until the indicated deadlines. After each deadline, one solution for each exercise will be chosen randomly, giving priority to students with a lower percentage (0 % - 30 %) achieved so far for this rating aspect. The selected students will be contacted to inform them about the presentation details.

The grading scale for the course is: 1: at least 90 %, 2: at least 80 %, 3: at least 65 %, 4: at least 50 %.

Examination topics

There are exercise sheets for the following topics: language processing and Python, accessing text corpora and lexical resources, processing raw text, writing structured programs, categorizing and tagging words, learning to classify text, extracting information from text, analyzing sentence structure, building feature based grammars, analyzing the meaning of sentences. The exam covers theoretical aspects from the corresponding chapters of the NLTK book, no coding is required for the exam.

Reading list

- Steven Bird, Ewan Klein, and Edward Loper. Natural Language Processing with Python. http://www.nltk.org/book/ O'Reilly Media, Inc., 2009.
- Kai-Uwe Carstensen et al., eds. Computerlinguistik und Sprachtechnologie - Eine Einführung. 3rd Edition, Springer Spektrum, 2010 (in German).
- Benjamin Bengfort, Rebecca Bilbro, Tony Ojeda. Applied Text Analysis with Python. O'Reilly Media, Inc., 2018.
- Hobson Lane, Cole Howard, Hannes Hapke. Natural Language Processing in Action. Understanding, analyzing, and generating text with Python. Manning Publications, 2019.
- Jacob Eisenstein. Introduction to Natural Language Processing. MIT Press, 2019.
- Delip Rao, Brian McMahan. Natural Language Processing with PyTorch. O'Reilly Media, Inc., 2019 (also available in German).
- Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, Harshit Surana. Practical Natural Language Processing. O'Reilly Media, Inc., 2020.

Association in the course directory

Module: NLP MSP

Last modified: Fr 18.10.2024 07:05