Universität Wien

340377 VU Introduction to Computational Linguistics (2022W)

6.00 ECTS (3.00 SWS), SPL 34 - Translationswissenschaft
Prüfungsimmanente Lehrveranstaltung
Moodle

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 40 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

  • Montag 10.10. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 17.10. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 24.10. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 31.10. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 07.11. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 14.11. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 28.11. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 05.12. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 12.12. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 09.01. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 16.01. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 23.01. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

Aims:
Students will become familiar with the beginnings, the progression over time, and the most recent methods in computational linguistics as well as their applications. Students will get the opportunity to implement Natural Language Processing algorithms (NLP) to see these methods in context and applied to real world applications. They will gain a deep understanding of the most recent approaches by discussion of cutting-edge research and hands-on experience.
In particular, by the end of the course they will be able to:
- understand the developments and the progression in the field of computational linguistics
- identify algorithms for solving various natural language processing problems
- implement these algorithms in the programming language Python
- use Python’s numerous libraries to solve real-world NLP problems
- identify the merits and issues of the most recent applications
- critically assess and discuss the most recent developments in the field

Contents:
- Theory and discussion of current research and state of the art applications
- Practical application of methods and algorithms in the form of problems solving with programming, using Python and NLTK

Didactic approach:
The content of this course is acquired by students in an interactive and blended way between in-class tasks and hands-on home assignments studying the research literature and implementing practical solutions of small NLP programming tasks. These small tasks build towards the final programming exercise at the end of the semester. In the first half of the semester, students will acquire theoretical foundations, as well as the necessary basics in Python and NLTK. In the second half of the semester, students will apply the knowledge they acquired in the first half and use their programming skills to solve NLP problems. By doing so, students will deepen their understanding of the theoretical foundations and prepare for new challenges.

The course is held in English.

Art der Leistungskontrolle und erlaubte Hilfsmittel

Students will apply the methods covered in the lecture to small programming assignments, using the programming language Python. They will present their acquired knowledge in a mid-term exam, and in a final programming project at the end of the semester. All assessments are open-book, except the mid-term exam.

Mindestanforderungen und Beurteilungsmaßstab

The assessment minimum requirements consist of three parts. At least 50 points must be achieved in each part. The sum of acquired points in each part translates into the final grade, as stated below.
Written mid-term (in class): 100 points (minimum 50)
Programming tasks throughout the semester (home assignments): 100 points (minimum 50)
Final programming projects (home assignment): 100 points (minimum 50)
Final grade:
>270 points: 1 (Sehr gut)
>240 points: 2 (Gut)
>210 points: 3 (Befriedigend)
>180 points: 4 (Genügend)
<=180 points: 5 (Nicht genügend)

Prüfungsstoff

The mid-term exam requires the knowledge of the entire theoretical part of the course. This includes all information on the lecture slides, as well as the associated topics in the listed literature.
The programming tasks and the final programming project require knowledge in the Python programming language, the Jupyter Notebook suite and the ability to apply the theoretical concepts from the lecture to real life problem solving.

Literatur

Steven Bird, Ewan Klein, and Edward Loper. Natural Language Processing with Python. http://www.nltk.org/book/ O'Reilly Media, Inc., 2009.
Cartensen, K.-U- (2017). Sprachtechnologie, Version 2.2 2017 http://kai-uwe-carstensen.de/Publikationen/Sprachtechnologie.pdf
Clark, A., Fox, C., & Lappin, S. (Eds.). (2013). The handbook of computational linguistics and natural language processing. John Wiley & Sons.
Eisenstein, J. (2018). Natural language processing. https://github.com/jacobeisenstein/gt-nlp-class/blob/master/notes/eisenstein-nlp-notes.pdf [Stand: 30.3.2020]
Jurafsky, D., & Martin, J. H. (2019). Speech and Language Processing (3rd (draft) ed.) https://web.stanford.edu/~jurafsky/slp3/ [Stand: 30.03.2020].
Python Webseite: https://www.python.org/
Examples and Tutorials for Python: https://www.w3schools.com/python/
RegEx: https://regexr.com/

Additional recommended resources:
Shaw, Z. 2014 Learn Python 3 the Hard Way. Addison-Wesley
Sambhaji, M. 2020 Quick Revision of Python programming: Easy and Fast. HighTechEasy Publishing
Koehn, P. 2020. Neural Machine Translation. Cambridge University Press
Koehn, P. 2010 Statistical Machine Translation. Cambridge University Press

Zuordnung im Vorlesungsverzeichnis

Letzte Änderung: Do 06.07.2023 17:08