Advanced Natural Language Processing (ANLP)

When Computers Understand Language: Work with modern AI, develop applications such as chatbots or translators, and understand how machines analyze and generate text.

Contents

• Classic NLP methods as a point of comparison: text representation, n-gram language models, classification and evaluation
• Deep learning for natural language processing: neural language models, word embeddings, sequence models and attention
• Transformer architecture and pre-training of large language models
• Adapting language models: fine-tuning, parameter-efficient training, instruction tuning and alignment
• Using language models: inference and decoding, prompting and in-context learning
• Building systems with language models: retrieval-augmented generation and tool-using agents
• Evaluating systems built with language models: self-built test data, metrics beyond accuracy, error analysis
• Ethics, safety and regulation in the use of NLP and AI systems
• Current developments in the field
• Practical exercises for every topic block, and a group project running through the semester

Competencies

• apply the foundations of deep learning for natural language processing,
• explain how language models work and where their limits are,
• develop a system based on language models for a concrete task,
• evaluate its results rigorously against classic reference methods,
• recognize typical failure modes of language models and analyze their causes,
• read current scientific publications in the field of NLP.

Literature

• D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd ed., draft released Jan. 6, 2026. [Online]. Available: https://web.stanford.edu/~jurafsky/slp3/ [Accessed: 19-Aug-2026].
• J. Eisenstein, Introduction to Natural Language Processing. Cambridge, MA, USA: The MIT Press, 2019.
• Y. Zhang and Z. Teng, Natural Language Processing: A Machine Learning Perspective. Cambridge, U.K.: Cambridge University Press, 2021.

Lecturer

• Prof. Dr. Kai Eckert

Recommended Previous Knowledge 

• Foundations in NLP (e.g. Bachelor-Course Natural Language Processing — Regular Expressions, N-Grams, Probabilistic Language Modeling, Vector Space Model)
• Foundations in Machine Learning (general methodology, Neural Networks, working with training and test data, evaluation, ...)
• Programming in Python (Jupyter Lab, Frameworks such as Pandas, NumPy, PyTorch, ...)

Module Details

Weekly Hours (SWS) 

Work Load