Howcroft, David ORCID: 0000-0002-0810-9065, Belz, Anya ORCID: 0000-0002-0552-8096, Gkatzia, Dimitra, Clinciu, Miruna, Hasan, Sadid, Mahamood, Saad ORCID: 0000-0003-2332-8749, Mille, Simon ORCID: 0000-0002-8852-2764, van Miltenburg, Emiel ORCID: 0000-0002-7143-8961, Santhanam, Sashank ORCID: 0000-0002-9412-3495 and Rieser, Verena ORCID: 0000-0001-6117-4395 (2020) Twenty years of confusion in human evaluation: NLG needs evaluation sheets and standardised definitions. In: 13th International Natural Language Generation Conference 2020 (INLG'20), 15-18 Dec 2020, Dublin, Ireland.