Re:Latent Dirichlet Allocation Surprisingly Well Correlated ...
by noelwelsh on Tuesday September 07, 2010 @09:31AM
(#1668813)
This post should be upvoted a zillion times. The correlations they report are really quite low and as such their claims are really quite bogus.
[ Parent
| on HN ]
Re:Latent Dirichlet Allocation Surprisingly Well Correlated ...
by will_critchlow on Tuesday September 07, 2010 @01:34PM
(#1669475)
I don't know if I saw my comment (looks like we posted at similar times). I'd be interested in your comments relative to that: there are a lot of factors this is quite a high correlation for a single one... (I think).