[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » courses » rg » 2013 » convolution-kernels

This is an old revision of the document!

Michael Collins, Nigel Duffy: Convolution kernels for natural language

Paper link

Questions

  1. What is a generative model, what is a discriminative model and what is their main difference?
  2. What are the “fairly strong independence assumptions” in PCFG? Come up with an example tree that can't be modelled by a PCFG.
  3. Derive and explain the formula for h(T1)*h(T2) on page 3 at the bottom.
  4. What is a convolution? Why are “convolution” kernels called like this?
  5. Find an error in one of the formulae in the paper.

[ Back to the navigation ] [ Back to the content ]