Twenty Years of Confusion in Human Evaluation: NLG Needs Evaluation Sheets and Standardised Definitions.
David M. HowcroftAnya BelzMiruna-Adriana ClinciuDimitra GkatziaSadid A HasanSaad MahamoodSimon MilleEmiel van MiltenburgSashank SanthanamVerena RieserPublished in: INLG (2020)