Translations:Word Embeddings/24/en: Difference between revisions

Revision as of 22:01, 27 April 2026

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Word Embeddings)

* '''Negative sampling''' — instead of computing the full {{Term|softmax}}, the model contrasts the true context word against <math>k</math> randomly sampled "negative" words.
* '''Hierarchical {{Term|softmax}}''' — organises the vocabulary in a binary tree, reducing the {{Term|softmax}} cost from <math>O(V)</math> to <math>O(\log V)</math>.

Negative sampling — instead of computing the full softmax, the model contrasts the true context word against $$ k $$ randomly sampled "negative" words.
Hierarchical softmax — organises the vocabulary in a binary tree, reducing the softmax cost from $$ O(V) $$ to $O(\log V)$ .

Revision as of 19:42, 27 April 2026 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source) ← Older edit		Revision as of 22:01, 27 April 2026 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source) Tag: Manual revert Newer edit →
Line 1:		Line 1:
	* '''Negative sampling''' — instead of computing the full ~~{{Term\|~~softmax}}, the model contrasts the true context word against <math>k</math> randomly sampled "negative" words.		* '''Negative sampling''' — instead of computing the full softmax, the model contrasts the true context word against <math>k</math> randomly sampled "negative" words.
	* '''Hierarchical ~~{{Term\|~~softmax}}''' — organises the vocabulary in a binary tree, reducing the ~~{{Term\|~~softmax}} cost from <math>O(V)</math> to <math>O(\log V)</math>.		* '''Hierarchical softmax''' — organises the vocabulary in a binary tree, reducing the softmax cost from <math>O(V)</math> to <math>O(\log V)</math>.