Gaussian Vector Space
Jump to navigation
Jump to search
A Gaussian Vector Space is a vector space of Gaussian points.
- See: Gaussian Embedding.
References
2016
- https://github.com/seomoz/word2gauss
- QUOTE: Python/Cython implementation of [[Luke Vilnis and Andrew McCallum Word Representations via Gaussian Embedding, ICLR 2015]] that represents each word as a multivariate Gaussian. Scales to (relatively) large corpora using Cython extensions and threading with asynchronous stochastic gradient descent (Adagrad).
2015
- (Vilnis & McCallum, 2015) ⇒ Luke Vilnis, and Andrew McCallum. (2015). “Word Representations via Gaussian Embedding.” In: International Conference on Learning Representations.
- QUOTE: Current work in lexical distributed representations maps each word to a point vector in low-dimensional space.