%0 Conference Proceedings
%T Analysing Data-To-Text Generation Benchmarks
%A Perez-Beltrachini, Laura
%A Gardent, Claire
%Y Alonso, Jose M.
%Y Bugarín, Alberto
%Y Reiter, Ehud
%S Proceedings of the 10th International Conference on Natural Language Generation
%D 2017
%8 September
%I Association for Computational Linguistics
%C Santiago de Compostela, Spain
%F perez-beltrachini-gardent-2017-analysing
%X A generation system can only be as good as the data it is trained on. In this short paper, we propose a methodology for analysing data-to-text corpora used for training Natural Language Generation (NLG) systems. We apply this methodology to three existing benchmarks. We conclude by eliciting a set of criteria for the creation of a data-to-text benchmark which could help better support the development, evaluation and comparison of linguistically sophisticated data-to-text generators.
%R 10.18653/v1/W17-3537
%U https://aclanthology.org/W17-3537
%U https://doi.org/10.18653/v1/W17-3537
%P 238-242