Analysing Data-To-Text Generation Benchmarks - Archive ouverte HAL Access content directly
Conference Papers Year :

Analysing Data-To-Text Generation Benchmarks

(1) , (2)
1
2

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.
Fichier principal
Vignette du fichier
d2tDatasetAnalysis.pdf (138.62 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01623832 , version 1 (25-10-2017)

Identifiers

  • HAL Id : hal-01623832 , version 1

Cite

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⟩
105 View
93 Download

Share

Gmail Facebook Twitter LinkedIn More