Re:Voyages in sentence space
by xtiansimon on Monday March 12, 2018 @10:06PM
(#16573403)
Warmer. _"English dump of Wikipedia that was sentence and word tokenized by NLTK."_ Wikipedia would certainly cover the morphology of a 'space'. I'm curious how the linguistic relations are derived from 'context', which I gather is what word2vec does. Although NLTK does have an interface to WordNet.
https://github.com/thoppe/transorthogonal-linguistics?files=...
Shayne Miel has observed that its results for the space from ‘sociology’ to ‘mathematics’ closely match an earlier XKCD comic:
https://groups.google.com/d/msg/gensim/a8PF8CInRKk/6XWcp87WB