Re:What it takes to build great machine learning products
by brendano on Monday April 16, 2012 @01:06PM
(#3848225)
Careful with the Collobert ICML-2008 paper. It has a very negative reputation among NLP researchers who actually know the area, just for its setup/evaluation. If you're interested in the methods (which I think are interesting), that group's later work is much improved.
[ Parent
| on HN ]