AI engineering glossary · NLP embeddings
What is out-of-vocabulary word?
Out-of-vocabulary word (also called OOV word, Unknown word): A word that does not appear in the tokeniser's or model's fixed vocabulary. Word-level systems typically replace it with a generic unknown token, losing its meaning; subword and byte-level systems avoid the problem by splitting it into known pieces.
Out-of-vocabulary word: an example
A word-level model trained on formal English sees "vadapav" for the first time and maps it to <unk>.
Related terms
More NLP embeddings terms
- Padding token
- Part-of-speech tagging
- Pointwise mutual information
- Positive pointwise mutual information
- Relation extraction
- Semantic role labelling
- Semantic similarity
- Semantic textual similarity
Where you learn it
Out-of-vocabulary word is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.