Deep Learning for NLP
Lecture and practice class

Deep Learning for NLP

All you need to know about contemporary natural langauge processing (NLP) using deep learning. More about foundations, less about particular frameworks or implementations.

Organization

The course will take place in presence.

  • Lecture: Tuesday 13:30-15:10, starting April 16.
  • Practice class: No practice class in presence. All information about exercises and homework will be distributed in Moodle.
  • Exam
    • Date/Time: 29.07.2024
    • Room: To be determined
  • Moodle Course: Link
    • The learning material is available from the Moodle eLeaning platform.
  • Requirements
    • To pass, each student has to take the written exam at the end of the semester.
    • There will also be homework assignments in the practice class which will contribute to your overall grade.

Teaching Staff

  • Dr. Thomas Arnold
  • Dr. Hendrik Schuff

We currently do not have fixed office hours, so please contact us by mail to get an appointment.

Course content

Main topics

  • Deep learning foundations (learning from data, learning problem formalization, loss functions, training with backpropagation, evaluation)
  • NLP as supervised task learning
  • Language representation (word embeddings, multi-lingual embeddings)
  • Prominent architectures (convoluational neural networks, recurrent neural networks)
  • Contemporary architectures and foundational models (transformers and BERT)
  • Applications (text classification, text generation, translation)