are you talking about the @fchollet paper?
-
-
Replying to @haldaume3 @_shrdlu_
Hal did sparse logreg over 6-grams of tokens, we did logreg over token embeddings.
1 reply 0 retweets 1 like
See paper for details. Note our models are just baselines, no hyperparam opt. 6-gram logreg strong baseline as well.
11:57 AM - 6 Nov 2016
0 replies
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.