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.