# What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think

> Research article (Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021) · cited 17× · AI/ML

**Wikidata**: [openalex:W3213713237](https://www.wikidata.org/wiki/openalex:W3213713237)  
**Source**: https://4ort.xyz/entity/what-happens-if-you-treat-ordinal-ratings-as-interval-data-human-evaluations-in-nlp-are-even-more-under-powered-than-you