News for hackers. Stuff that matters.

A comment on King – man + woman is queen; but why?. Parent comment

Re:King – man + woman is queen; but why? by DonaldFisk on Saturday January 07, 2017 @07:14PM (#13347463)
The first quote is simply not true. Symbols, even in Lisp, have properties (as well as values and possibly function values), i.e. they have deep structure. In general, symbols are explicitly linked to other symbols or algorithms. These links are the symbolic analogue of the vectors in word2vec, except that they are explicit so you can see what they mean, but you have to enter them manually or use a more complex machine learning algorithm.

The author of the computer vision blog post doesn't seem to know much about symbolic AI. Some of the comments point this out.

[ Parent | on HN ]
Re:King – man + woman is queen; but why? by paulsutter on Saturday January 07, 2017 @07:50PM (#13347557)
The various benchmarks are a great opportunity to demonstrate the superiority of the symbolic approach over the neural network based models. I encourage you to try, there's no better way to dispel the doubters.
[ Parent | on HN ]
Re:King – man + woman is queen; but why? by DonaldFisk on Saturday January 07, 2017 @08:35PM (#13347734)
I don't think they're suitable for the same tasks, so I don't consider the two approaches to be in competition with each other. It's also very difficult if you're one person with limited time up against companies the size of Google.

I'm busy on other things at the moment, but I intend to develop a rule-based system some time soon. I can rule out a neural network straight away because there's no data available, the rules are explicit, well documented, and have to be followed, and the system has to justify its reasoning.

That is not to say I wouldn't consider using a neural network for a perception task.

[ Parent | on HN ]
Re:King – man + woman is queen; but why? by nitrogen on Saturday January 07, 2017 @09:29PM (#13347908)
Is anybody working on using a neural network to build and update a symbolic graph, and vice versa? Or at least using a symbolic graph as an input to a NLP neural network, so the network could learn to rely on the symbolic graph when it is useful?
[ Parent | on HN ]
Re:King – man + woman is queen; but why? by rspeer on Saturday January 07, 2017 @11:19PM (#13348213)
Yes. ConceptNet [1] and distributional word embeddings go really well together, and can compare word meanings better than either one alone. Here's the preprint of the AAAI 2017 paper [2].

[1] http://www.conceptnet.io/

[2] https://arxiv.org/pdf/1612.03975v1.pdf

[ Parent | on HN ]