Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language

Re:Critical Behavior from Deep Dynamics: A Hidden Dimension ... by TheOtherHobbes on Wednesday July 13, 2016 @09:39AM (#12086016)

Personally, no. I think all of these models are essentially trivial and a long way from genuine NLP.

That doesn't mean they're not useful in very narrow domains. But language is pretty much the definition of the ultimate wide domain, and trying to cover it with statistical correlations makes as much sense as word counting Shakespeare to try to generate some new plays.

[ Parent | on HN ]

Re:Critical Behavior from Deep Dynamics: A Hidden Dimension ... by mark_l_watson on Wednesday July 13, 2016 @09:50AM (#12086091)

I think you might be pleasantly surprised by recent results using DL and LSTM for building models of natural language. The next advancement I would like to see is handling anaphora resolution (resolving pronouns to previous noun phrases in text, resolving words like 'there' to a place mentioned elsewhere in text, etc.) Progress has been so rapid that I bet I don't have to wait long.

[ Parent | on HN ]

Re:Critical Behavior from Deep Dynamics: A Hidden Dimension ... by nschucher on Wednesday July 13, 2016 @09:57AM (#12086145)

Have you seen the results from Dynamic Memory Networks? [0]

The relevant example from the paper:

  I: Jane went to the hallway.
  I: Mary walked to the bathroom.
  I: Sandra went to the garden.
  I: Daniel went back to the garden.
  I: Sandra took the milk there.
  Q: Where is the milk?
  A: garden

Obviously just a toy task, but as you said, progress is rapid!

[0]: http://arxiv.org/abs/1506.07285

[ Parent | on HN ]

Re:Critical Behavior from Deep Dynamics: A Hidden Dimension ... by mark_l_watson on Wednesday July 13, 2016 @10:12AM (#12086254)

Thanks for the link!

[ Parent | on HN ]

Re:Critical Behavior from Deep Dynamics: A Hidden Dimension ... by crypto5 on Wednesday July 13, 2016 @03:31PM (#12088974)

> I think you might be pleasantly surprised by recent results using DL and LSTM for building models of natural language.

What exactly those models are modelling?

[ Parent | on HN ]