News for hackers. Stuff that matters.
Re:Natural Language Basics with TextBlob by imh on Monday September 28, 2015 @02:01AM (#10289118)
Wouldn't this require larger datasets? That isn't always an option. I'm imagining that a smaller, more computationally efficient network could learn nearly as well with fewer data points given these heavily engineered features. Is that off base?
Re:Natural Language Basics with TextBlob by nl on Monday September 28, 2015 @08:07AM (#10289980)
Basically, no. See http://karpathy.github.io/2015/05/21/rnn-effectiveness/

He gets pretty amazing results with a corpus size around 10M.

Re:Natural Language Basics with TextBlob by imh on Monday September 28, 2015 @06:55PM (#10293725)
But that takes ages to train!
Re:Natural Language Basics with TextBlob by nl on Tuesday September 29, 2015 @07:24AM (#10295570)
So something like Jason Weston's state-of-the-art attention-NN based sentence summarizer took ~4 days to train.

You'd easily spend that time doing manual feature engineering just to build a baseline system.