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

David M. Howcroft, Verena Rieser

2021 (modified: 30 Nov 2021)EMNLP (1) 2021Readers: Everyone
Abstract: David M. Howcroft, Verena Rieser. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.
0 Replies