[Corpora-List] Word-embedding distribution in space

Andrey Kutuzov akutuzov72 at gmail.com
Wed May 31 18:40:36 CEST 2017


Hi Fabio,

May be, this paper will be of help? https://arxiv.org/pdf/1412.6568.pdf

31.05.2017 17:37, Fabio Tamburini wrote:
> Dear Corpora members,
>
> I am trying to understand if the word-embeddings produced by one of the
> available method (say word2vec) follow a specific distribution in space.
>
> More precisely: given a set of n-dim normalised embeddings produced from
> a corpus, is there any study that analysed the vectors distribution over
> the n-dimensional sphere of radius 1?
>
> We cannot certainly assume a uniform distribution and it is more
> realistic a distribution driven by the small-world hypothesis/rule, but
> I am not aware of any precise result about this.
>
> Any pointer is very appreciated and all the replies, if numerous, will
> be collected in a digest.
>
> Many thanks
>
> Best
> Fabio
>
>
> -----------------------------------------------------------------------------
>
> Fabio Tamburini, PhD
> Associate Professor
> FICLIT - University of Bologna - ITALY
> E-mail: fabio.tamburini at unibo.it
> -----------------------------------------------------------------------------
>
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora

-- Andrey



More information about the Corpora mailing list