prEN ISO/IEC 23282 — (WI=JT021012)Artificial Intelligence - Evaluation methods for accurate natural language processing systems (ISO/IEC DIS 23282:2026)
CEN-CENELEC · 2026-08-27 · EU · verified record
Themes: Artificial intelligence · Cross-sector · Online platforms
Ecosystems: EU AI Act
Register: Official CEN-CENELEC CEN/CLC/JTC 21 Artificial Intelligence work programme; Project: prEN ISO/IEC 23282 (WI=JT021012)Artificial Intelligence - Evaluation methods for accurate natural language processing systems (ISO/IEC DIS 23282:2026); Status: Under Approval; Initial date: 2023-11-22; Current stage: 2026-08-27; Next stage: 2026-09-03; Forecasted voting date: 2027-07-26
The European Committee for Standardization is one of three European Standardization Organizations (together with CENELEC and ETSI) that have been officially recognized by the European Union and by the European Free Trade Association (EFTA) as being responsible for developing and defining voluntary standards at European level. - | This standard contributes to the following SDG: | Reference | prEN ISO/IEC 23282 | |---|---| | Title | Artificial Intelligence - Evaluation methods for accurate natural language processing systems (ISO/IEC DIS 23282:2026) | | Work Item Number | JT021012 | | Abstract/Scope | This document specifies the evaluation of natural language processing systems, in the sense of measuring the quality of a system’s results to assess its functional suitability. It provides a definition of evaluation methods for those systems, together with guidance on how to select, implement and interpret those evaluation methods. This document covers quantitative metrics as well as other evaluation methods. It includes requirements on the implementation of the described metrics, and further requirements on the technical resources involved in the evaluation process.…
Sign in to read this record in the app with full provenance, themes and related developments — free, 20 searches a day, no card needed.
Read in Vellum Search → Official source ↗Source content © CEN-CENELEC — served per the publisher's reuse terms. Vellum metadata & summary © Vellum AI Group Ltd. Reuse & rights.