King – man + woman is queen; but why?

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 ]