Ah...now I get it! Excerpt from this important article: "We use - TopicsExpress



          

Ah...now I get it! Excerpt from this important article: "We use two metrics for [our] evaluation. The first ...is a local approximation to log-likelihood, and we therefore dub it LOcal Log-likelihood, or LOL-likelihood for short. Our second metric computes the rank of the human-generated jokes in the distribution of all possible jokes sorted decreasingly by their LOL-likelihood. This Rank OF Likelihood (ROFL) is computed relative to the number of all possible jokes, and like LOL-likelihood is averaged over all the jokes in our development data." homepages.inf.ed.ac.uk/s0894589/petrovic13unsupervised.pdf
Posted on: Sat, 03 Aug 2013 18:45:38 +0000

Trending Topics



Recently Viewed Topics




© 2015