Disentangling Factors of Variation via Generative Entangling — mentioned by jkldotio

Wed, 23 Mar 2016 23:12:08 GMT

I don't speak with any authority on this. With word2vec you can do operations like king - man + woman and the nearest vector will be queen. Similarly capital cities will be in a similar relationship to their countries so if you take Rome - Italy + Spain you will be nearest to Madrid. That permits limited reasoning by analogy and there are some analogy benchmark tasks which those word models perform reasonably well on, effectively answering loads of questions like "Madrid is to Spain as Rome is to ____?". This model is more complex and seems to be using a series of techniques to "disentangle"…

Paper and discussion history. A mention is not an endorsement.

Disentangling Factors of Variation via Generative Entangling · HackerPapers discussions

Disentangling Factors of Variation via Generative Entangling — mentioned by jkldotio