LIN 389C: Topic list Fall 2018

The consensus was that we should have several main themes. The following themes were mentioned:

  • Neural models: Autoencoders, variational autoencoders.
    Generative models were also mentioned -- was that in this context?
  • "Thinking, fast and slow": Probabilistic programming languages
  • Working with less data: semi-supervised learning, domain adaptation, distant supervision
  • Applications:
    • Multimodality
    • Entity-based modeling
Additional applications not mentioned in our discussion but that I think we should add: summarization, narrative modeling.

We will choose from this topic list in our first meeting after the break.