Abstract

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.

Begin

2024-02-02

WI

JT021012

Planned document number

DIN EN ISO/IEC 23282

Project number

04301055

Responsible national committee

NA 105-00-06-01 GAK - Joint working group NAT/NIA: Natural Language Processing  

Responsible european committee

CEN/CLC/JTC 21/WG 3 - Engineering aspects  

Responsible international committee

ISO/IEC JTC 1/SC 42/JWG 5 - Joint Working Group ISO/IEC JTC1/SC42 - ISO/TC 37 WG: Natural language processing  

draft standard

Artificial Intelligence - Evaluation methods for accurate natural language processing systems (ISO/IEC DIS 23282:2026); German and English version prEN ISO/IEC 23282:2026
2026-10
Order from DIN Media