230015 Lab: Implementing neuronal networks for NLP (S) (SoSe 2022)

This seminar explores applications and implementations of neural network methods for computational linguistics research. We apply classical and deep neural networks to selected problems in natural language processing, focusing on so-called sequence-to-sequence models (used in, e.g., machine translation, language generation, dialogue modeling). In addition, we also touch upon several multi-modal NLP problems.

Recent advancements in neural networks promise to learn data representations and relevant features from the data itself instead of task-specific feature engineering. They have progressed the state-of-the-art in several NLP-related tasks, in some cases significantly. The seminar includes hands-on sessions to learn relevant programming techniques, e.g., using and applying recurrent neural networks and state-of-the-art transformer models to sequential problems in Python/PyTorch.

The course will be taught in English.

In this seminar, students learn to
- aspects of machine learning, neural networks, computational linguistics
- to apply these methods to selected natural language processing problems

To successfully pass, we ask participants
• to hand in 2-3 small homework assignments
• to present a paper or Python library/package