Related courses
| No. | Type | Course name | Participation | TWS |
| 38501 | VÜ | Natural Language Processing | Compulsory | 3 |
| 38502 | P | Natural Language Processing | Compulsory | 3 |
| Total (Compulsory and elective) | 6 | |||
Recommended prerequisites
Students should have basic knowledge of computer science, in particular experience with algorithms and programming skills in Python.
Qualification objectives
The aim of the courses in this module is to familiarize students with special techniques of Natural Language Processing. In particular, students will learn how to ensure the quality, reliability and performance of complex language models by selecting appropriate development and evaluation methods.
Contents
Students learn about the most important phenomena in natural languages at different levels of granularity, from the combination of sounds to the meaning of words, sentences and texts.
They are introduced to the most important symbolic and statistical approaches of Natural Language Processing (NLP) for modeling these phenomena. All theoretical topics are accompanied by exercises dealing with these phenomena and demonstrating their application in practical scenarios, such as spelling correction, automatic completion, keyword extraction, topic recognition, recognition of named entities (proper names), relation extraction, synonym recognition, etc.
In the practical course, the contents of the lecture are applied in the context of an exemplary NLP project.
Literature
- Dan Jurafsky, James H. Martin: Speech and Language Processing, 3. Auflage, 2023. https://web.stanford.edu/~jurafsky/slp3/
- Steven Bird, Ewan Klein, Edward Loper: Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit, 2019. https://www.nltk.org/book/
- Akshay Kulkarni, Adarsha Shivananda: Natural Language Processing Recipes: Unlocking Text Data with Machine Learning and Deep Learning Using Python, Apress, 2021.
Proof of performance
Proof of performance for the module is a portfolio made up of the individual performances in the two sub-courses. The individual assessments required are as follows:
- 38501: Written examination of 60 minutes or oral examination of 30 minutes. The type of examination will be announced at the beginning of the module.
- 38502: Presentation, processing time: 4 weeks, duration 20 minutes.
The performance in the lecture (with exercise) and in the practical course are included in the grade in equal proportions.
Applicability
Participation in the courses of this compulsory elective module enables students to take on a Master's thesis in the field of Data Science with a focus on Natural Language Processing.
Duration and frequency
The module lasts 2 trimesters and begins each year in WT.