The master module Deep Learning for Text Analytics (DELTA) is offered at the Humboldt-University of Berlin by the Chair of Information Systems.

DELTA introduces students to deep learning and natural language processing. We discuss algorithmic foundations, several deep learning methodologies, and their applications in business and society.

The module draws inspiration from several excellent resources including but not limited to:

• Natural Language Processing with Deep Learning by Stanford University
• Several awesome educational posts in Jay Alammar's blog
• The fantastic interactive e-book Dive into Deep Learning

We greatly appreciate the provision of this great content and highlight its contributions to the design of DELTA.

The module is offered every summer semester. Weekly sessions split into a two hour lecture session and a two hour tutorial session. The lecture introduces relevant concepts in the scope of the course. Lecture sessions are accompanied by Jupyter notebooks that demonstrate these concepts using the Python programming language and various Python libraries for deep learning and NLP. Providing working examples and executable codes, the Jupyter notebooks are meant for self-study. To deepen their understanding of the covered topics, students receive programming tasks as homework. The tutorial sessions provide a forum to discuss solutions to the homework task as well as general questions.

While the time and location of lecture and tutorial sessions may be subject to change, we aim at offering lecture/tutorial sessions as follows: Lecture: Thu, 10.15 - 11.45,
Q&A Session: Tue, 16:15 - 17:45,
Exercise 1: Thu, 12.15 - 13.45,

Topics covered in DELTA include but are not limited to:

• Fundamentals of artificial neural networks
• Fundamentals of natural language processing (NLP)
  • NLP tasks and use cases
  • Early forms of NLP (dictionaries, bag of word model)
  • Word embeddings
• Neural network architectures for sequential and unstructured data
  • Recurrent and gated neural networks
  • RNNs for language modeling
• State-of-the-art NLP approaches
  • Attention and Transformers
  • NLP transfer learning

The repository provides Jupyter notebooks that revisit concepts covered in the lecture in the folder lecture_codes. Additionally, the folder exercises provides another set of Jupyter notebooks, which task students to practice their Python and Deep Learning skills on programming exercises. The notebooks starts with a short demo, which serves revision purposes. The remaining part of the exercise notebooks are related to programming tasks, which the students should try to solve themselves; possibly together with peers in their study group.

More detailed information on the coures format, organization, and logistics is available on the DELTA Moodle page. That page also provides slides for lecture sessions and video recordings.