Inhalt

[ 536DASCNLPK20 ] KV Natural Language Processing

Versionsauswahl
Workload Education level Study areas Responsible person Hours per week Coordinating university
3 ECTS B3 - Bachelor's programme 3. year Computer Science Navid Rekabsaz 2 hpw Johannes Kepler University Linz
Detailed information
Original study plan Bachelor's programme Artificial Intelligence 2020W
Objectives Natural Language Processing (NLP) is the study of how to understand and process human language using computational methods. The aim of the course is to provide in depth knowledge on the essential elements of NLP, particularly based on machine learning and neural networks. Upon completing, students will be able to understand the mechanisms behind NLP systems, applied to applications such as language modeling, document classification, sentiment analysis, information retrieval, computational social science, and detection of societal biases. The students will be able to propose and weigh various solutions to NLP problems. Through assignments, students gain the know-how to develop effective NLP solutions with machine learning and neural networks for tasks such as document classification and sentiment analysis.
Subject The course covers the following topics:

  • Text processing
  • Sentiment analysis with machine learning
  • Language modeling with neural networks
  • Word embedding models (word2vec, GloVe, etc.)
  • Learning compositional embeddings
  • Contextualized word embeddings (practical walkthrough)
  • Principles of Information Retrieval
  • Computational social science with NLP
  • Societal biases in NLP
Criteria for evaluation Oral or written exam at the end of the semester. Three assignments during the course.
Methods Slide presentations with examples on blackboard, as well as one in-class practice-oriented workshop.
Language English
Changing subject? No
Further information For further information visit https://www.jku.at/en/institute-of-computational-perception/teaching/all-courses/natural-language-processing/
On-site course
Maximum number of participants 35
Assignment procedure Direct assignment