AI engineering glossary · NLP embeddings
What is one-hot word vector?
One-hot word vector (also called One-hot representation): A vector as long as the vocabulary with a single 1 at the word's position and 0 everywhere else. It uniquely identifies a word but is huge, mostly zeros, and treats every pair of words as equally unrelated.
One-hot word vector: an example
In a 5-word vocabulary [cat, dog, car, bus, tea], "car" is [0, 0, 1, 0, 0].
Related terms
More NLP embeddings terms
- Out-of-vocabulary word
- Padding token
- Part-of-speech tagging
- Pointwise mutual information
- Positive pointwise mutual information
- Relation extraction
- Semantic role labelling
- Semantic similarity
Where you learn it
One-hot word vector is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.