Ruprecht-Karls-Universität Heidelberg
Institut für Computerlinguistik

Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg

Oldies but Goldies


Course Module Abbreviation Credit Points
BA-2010 AS-CL 8 LP
BA-2010[100%|75%] CS-CL 6 LP
BA-2010[50%] BS-CL 6 LP
BA-2010[25%] BS-AC 4 LP
Master SS-CL, SS-TAC 8 LP
Lecturer/-innen Michael Staniek
Module Type Proseminar / Hauptseminar
Language Englisch
First Session 12.11.2020
Time and Place Thursday, 16:15-17:45, Online
End of Commitment Period tbd.

Prerequisite for Participation

  • Mathematical Foundations of CL (or a comparable introductory class to linear algebra and theory of probability)
  • Programming I (Python)
  • Statistical Methods for CL (or a comparable introductory class to machine learning)
  • Assessment

    Presentation Project


    This seminar is aimed at topics that are useful in general for Natural Language Processing but are not part of the official curriculum. Many of the algorithms in this had a main application that is not state of the art in NLP anymore, but still have side applications where they can help to improve current state of the art models. This seminar mostly deals with the basic of these algorithms. Here a rough topic list:

  • Expectation Maximization
  • Conditional Random Fields
  • Variational Inference
  • Gaussian Processes
  • Evolutionary algorithms
  • Linear Programming
  • Reparameterization
  • Lagrangian Relaxation
  • Structured Prediction
  • Decision Trees and Random Forests
  • Dynamic Programming
  • Attendants are expected to prepare one topic for the other students. Students are also expected to have a project with one Algorithm at the end of the exam.

    Module Overview


    Datum Sitzung Materialien

    » weitere Kursmaterialien

    zum Seitenanfang