# Twenty Years of Confusion in Human Evaluation: NLG Needs Evaluation Sheets and Standardised Definitions

> Research article (Proceedings of the 13th International Conference on Natural Language Generation, 2020) · cited 116× · AI/ML

**Wikidata**: [openalex:W3109862485](https://www.wikidata.org/wiki/openalex:W3109862485)  
**Source**: https://4ort.xyz/entity/twenty-years-of-confusion-in-human-evaluation-nlg-needs-evaluation-sheets-and-standardised-definitions