20-00-0596-se Text Analytics

Lehrende: Prof. Dr. phil. Iryna Gurevych

Veranstaltungsart: Seminar

Orga-Einheit: FB20 Informatik

Anzeige im Stundenplan: Text Analytics

Fach:

Anrechenbar für:

Semesterwochenstunden: 2

Unterrichtssprache: Deutsch

Min. | Max. Teilnehmerzahl: - | -

Lehrinhalte:
Text Analytics: Commonsense Reasoning for Language Understanding

Commonsense knowledge, like knowing that “not everything that looks like fruits is edible” or “rain makes things wet“, is essential for humans to live and communicate. To better understand humans and take more reasonable actions, learning and incorporating commonsense is essential for AI.  The seminar will cover the latest research on commonsense modeling for natural language processing. We will talk about casting common sense tasks as NLP problems; review existing methods and benchmarks; assess our current knowledge about commonsense capabilities of language models, and investigate ways to incorporate commonsense into downstream tasks.

Literatur:
Will be announced during the seminar.

Voraussetzungen:
Each student is expected to:

• attend the online seminar sessions and actively contribute to discussions during the seminar,
  
• develop a presentation on a topic relevant to the seminar,
  
• present the topic and answer the questions from the audience, and
  
• write a paper on the chosen topic.
  

Weitere Informationen:
The first sessions will consist of introductory lectures to cover the basics of machine learning methods used for NLP tasks. The program for the remainder of the seminar will be determined according to the number of participants.