On Thu, Dec 19, 2019 at 9:25 PM <[email protected]> wrote:
> Also, how does a hyperbolic space improve w2v? I looked up images of > hyperbolic structures and they just look like another web. Are you pruning > some connections perhaps? > Hyperbolic embedding has been proven useful for Word2vec, as it can reduce the vector representation's dimension, ie, use fewer numbers. This idea can be extended from Word2vec to Sentence2vec. But this idea seems not useful when it comes to the mental state being composed of propositions (sentences). This composition has a set structure (ie, permutation invariant) which is different from a list structure (simple concatenation of vectors). So I abandoned this direction... ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcfe7cc93841eec23-Md3168074fe8f766a8f87177d Delivery options: https://agi.topicbox.com/groups/agi/subscription
