English

Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)

Computation and Language 2019-10-11 v1

Abstract

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: we synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Du\v{s}ek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.

Keywords

Cite

@article{arxiv.1910.04731,
  title  = {Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)},
  author = {Ondřej Dušek and Karin Sevegnani and Ioannis Konstas and Verena Rieser},
  journal= {arXiv preprint arXiv:1910.04731},
  year   = {2019}
}

Comments

Accepted as a short paper at INLG 2019

R2 v1 2026-06-23T11:40:05.835Z