Turns out one of the top performing models on SNLI (>86% accuracy) is essentially a bag-of-words model. Interesting. http://arxiv.org/pdf/1606.01933v1.pdf …
-
There's a strong need for revisiting baselines rather than relying on an older paper to have done it well, esp as techniques improve
I've found shallow CNNs or even logreg to frequently outperform RNNs with attention on text classification too...
-
-
yet most people don't even try these, they jump directly to LSTM or GRU. This is a consequence of DL hype
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
RNN with attention is a total overkill for most text cat. And won't work well.
-
agreed, yet some fairly big names in DL NLP rely on it reflexively for sentence pair scoring or text clf.
End of conversation
New conversation -
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.