Understanding Deep Learning for Natural Language Understanding

Description

This seminar will highlight recent work in Deep Learning for Natural Language Understanding, considering both the theoretical background and existing implementations.

We will cover methods for learning semantic embeddings of words, sentences and documents, methods for learning embeddings of knowlegde bases, as well as neural network architectures relevant for sentence and document-level machine learning tasks.

Organization

• Block seminar in the second half of the semester; there will be one teaching block and one student presentation block
• Kick-off meeting with distribution of topics: Tuesday, October 20 2015, 13.30, S2|02 D017
• Teaching block:
  • Monday, December 7 2015, 9-13, S2|02 A213
  • Tuesday, December 8 2015, 9-13, S2|02 E302
• Presentation block:
  • Monday, February 1st 2016, 9-13, S2|02 A213

Expectation

Each student is expected to

• attend the seminar sessions and actively contribute to the discussion in the seminar
• prepare a presentation on the assigned topic
• present this presentation and be able to answer questions from the audience
• prepare a term paper on the topic

Lecturers

Dr. Judith Eckle-Kohler (office hours: please resigster by e-mail)