Skip to content

Generative AI & LLMs

Word2Vec

Word to vector

Methods that turn words into numerical patterns by learning which words tend to appear near each other.

Example

Words used in similar contexts receive related vectors.

Why people use it

It gives words numerical descriptions that help computers compare their patterns of use.

What you'll hear

“Words used in similar places end up closer together.”

What this means for you

Consider ambiguity when using fixed word vectors.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does Word2Vec give a word a fresh meaning for every sentence?
Standard Word2Vec gives each word a fixed numerical description instead of changing it for every sentence.
Can it reflect stereotypes in its teaching material?
Yes. Patterns in the source text can include social biases and associations.
Does a close match mean two words are interchangeable?
No. Similar usage does not make their meanings identical in every sentence.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice