Tokenization and text representation · MLD-0855
Out-of-vocabulary
An item not directly represented in a fixed vocabulary.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Encounter an unseen word in a word-level model.
Original caveat
Subword or byte systems can often represent unseen words compositionally.
Context and aliases
Level: Intermediate. Stages: Data · Training · Inference.
Tags: NLP · SLM · LLM.
Aliases: OOV.
Related concepts
Concepts linking here
Original references
- Hugging Face: chat templates ↗ · Reference link
- Transformers glossary ↗ · Consulted
- Hugging Face: tokenization algorithms ↗ · Consulted
- Original reference URL ↗