Ruprecht-Karls-Universität Heidelberg
Institut für Computerlinguistik

Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg

Story Generation

Kursbeschreibung

Studiengang Modulkürzel Leistungs-
bewertung
BA-2010 AS-CL 8 LP
BA-2010 AS-FL 8 LP
BA-2010[100%|75%] CS-CL 6 LP
BA-2010[50%] BS-CL 6 LP
BA-2010[25%] BS-AC, BS-FL 4 LP
Master SS-CL, SS-TAC, SS-FAL 8 LP
Dozenten/-innen Julius Steen
Veranstaltungsart Proseminar / Hauptseminar
Sprache English
Erster Termin 11.11.2020
Zeit und Ort Mittwoch, 16:15-17:45, Online
Commitment-Frist tbd.

Teilnahmevoraussetzungen

  • Statistical Methods for CL (or comparable)
  • Students are expected to have some mathematical maturity and basic familiarity with computational tools (such as numpy).
  • Leistungsnachweis

  • Active Participation
  • Presentation
  • Second presentation, term paper or implementation project
  • Inhalt

    Telling and understanding stories is an activity that heavily relates to how humans perceive and understand the world. As such, the task of automatically generating stories has attracted considerable research interest spanning back multiple decades.

    In this seminar we will take a look at both the history of the task and the current state of the art in story generation.
    We will start with early symbolic approaches that rely on manually defining domain models to generate stories from. We will then move towards more modern approaches that leverage the power of neural networks and pretrained language models to generate stories in an open setting without relying on extensive manually created resources.

    Kursübersicht

    Seminarplan

    Datum Sitzung Materialien

    Literatur

    A literature list will be provided at the beginning of the seminar

    » weitere Kursmaterialien

    zum Seitenanfang