Instructors: Dr. rer. pol. Steffen Eger
Event type:
Integrated Course
Org-unit: Dept. 20 - Computer Science
Displayed in timetable as:
DL4NLP
Subject:
Crediting for:
Hours per week:
4
Language of instruction:
German
Min. | Max. participants:
- | -
Course Contents:
The lecture provides an introduction to the foundational concepts of deep learning and their application to problems in the area of natural language processing (NLP)
Main content:
- foundations of deep learning (e.g. feed-forward networks, hidden layers, backpropagation, activation functions, loss functions)
- word embeddings: theory, different approaches and models, application as features for machine learning
- different architectures of neuronal networks (e.g. recurrent NN, recursive NN, convolutional NN, encoder-decoder models) and their application for groups of NLP problems such as document classification (e.g. spam detection), sequence labeling (e.g. POS-tagging, Named Entity Recognition) and more complex structure prediction (e.g. Chunking, Parsing, Semantic Role Labeling)
Literature:
Can use this as introductory material:
@book{Goodfellow-et-al-2016,
title={Deep Learning},
author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
publisher={MIT Press},
note={\url{http://www.deeplearningbook.org}},
year={2016}
}
Further literature is announced during the lecture.
Preconditions:
Basic knowledge of mathematics and programming
|