Abstract : 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 micro-planner i.e., systems which given some input must produce a text verbalising exactly this input. We apply this methodology to three existing benchmarks and we elicite 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.
Laura Perez-Beltrachini, Claire Gardent. Analysing Data-To-Text Generation Benchmarks. The 10th International Natural Language Generation conference., Sep 2017, Santiago de Compostelle, Spain. ⟨hal-01623832⟩
