Re:"We need a pony. And the moon on a stick. By next Thursday."
by vog on Wednesday June 04, 2014 @09:52AM
(#7845510)
It would be interesting to know how this algorithm behaved on fundamentalist texts. (see Poe's law, https://en.wikipedia.org/wiki/Poe%27s_law)
Re:"We need a pony. And the moon on a stick. By next Thursday."
by rainforest on Wednesday June 04, 2014 @11:01AM
(#7845914)
This paper appears to claim up to 91% accuracy (precision) [1] by looking at hashtags, with a description of the approach they use (and a link to the software). The approaches probably aren't directly comparable since one depends on hashtags while the other doesn't though.
Re:"We need a pony. And the moon on a stick. By next Thursday."
by opium_tea on Wednesday June 04, 2014 @10:20AM
(#7845659)
This video suggests their early prototypes required some further calibration:
https://www.youtube.com/watch?v=mSy5mEcmgwU
Re:"We need a pony. And the moon on a stick. By next Thursday."
by eli_gottlieb on Wednesday June 04, 2014 @11:34AM
(#7846151)
Yeah, really. It's creating a whole human mind that's hard. Particular, isolated tasks or features about particular things in particular cultures are not actually that hard to learn/classify in themselves, as your data corpus will be more uniform than if you were trying to perform some more general cognition across a wider variety of contexts. More uniformity makes it easier to learn.
[1] http://www.bbc.co.uk/news/technology-23160583
[2] http://spotter.com/