Terms related to natural language processing · 3.6.8
natural language generation
a task that turns data carrying meaning into natural language
What this term settles
The definition fixes what natural language generation means inside this vocabulary and, just as usefully, where the boundary sits. A reader who means something wider or narrower is using a different term and should say so.
Who it binds
The entry has no shall in it, and the force of natural language generation comes from use: once it appears in a procedure or a supplier term, this is the meaning the reader may rely on.
What to do in your practice
Put natural language generation in the controlled vocabulary with its citation, an owner and a review date. Then test the inventory and the policy against the entry and record every place the firm uses a different word for the same thing.
Evidence an auditor or regulator asks for
- A controlled vocabulary entry for natural language generation with the citation 3.6.8, an owner and a review date.An auditor can check that natural language generation is controlled rather than assumed.
- A product description that names the language task and the input and output it handles. The row names natural language generation.Shows natural language generation in use in the artefact the firm relies on, not only in a glossary.
- An evaluation set with the language, the domain and the scoring rule. The record carries the natural language generation entry and its date.The product description mixes the task with the model, so a change of model reads as a change of task. The gap is tested against natural language generation.
Common gaps this page catches
- natural language generation is used in the language task in the product description without a written definition, so two teams can mean different things.
- The entry for natural language generation exists in a glossary but not in the system record, so the two disagree at the point of use.
What to prepare before the amendment lands
Take the next policy revision and replace the loose use of natural language generation with the entry and its citation. Record the change in the vocabulary change log.
How to test it here
Take one live artefact rather than a template, find the sentence or field where natural language generation is used, and put this page beside it. Record the answer, the artefact and the date, because that record is the evidence and a glossary entry on its own is only an intention.
What this page does not claim
The page does not reproduce the standard, certify the firm or predict the wording the amendment will use; it states natural language generation at the claim level "definition" and stops where the public record stops.
Common questions
- What does natural language generation mean in ISO 22989?
- a task that turns data carrying meaning into natural language
- What evidence should we keep for 3.6.8?
- A controlled vocabulary entry for natural language generation with the citation 3.6.8, an owner and a review date. A product description that names the language task and the input and output it handles. The row names natural language generation.
- Is natural language generation a requirement?
- No: natural language generation is a definition or clause of a terminology standard, and it becomes binding only when a firm writes it into a policy, a contract or a procedure, or when another standard incorporates it.
Related units
Source. ISO/IEC 22989:2022, Clause 3.6.8, Terms and definitions. Open the ISO public entry. Retrieved 21 October 2026.
https://www.iso.org/obp/ui/en/#iso:std:iso-iec:22989:ed-1:v1:en
ISO catalogue record 88145, the amendment status, stage and dates. Catalogue record 74296, the base standard.
Claim level: definition. The definition is in the public preview. This page states it in our own words and does not reproduce the text.
Last updated: 2026-10-21 · Markdown version · Check your vocabulary