English

Data-driven Natural Language Generation: Paving the Road to Success

Computation and Language 2017-06-30 v1

Abstract

We argue that there are currently two major bottlenecks to the commercial use of statistical machine learning approaches for natural language generation (NLG): (a) The lack of reliable automatic evaluation metrics for NLG, and (b) The scarcity of high quality in-domain corpora. We address the first problem by thoroughly analysing current evaluation metrics and motivating the need for a new, more reliable metric. The second problem is addressed by presenting a novel framework for developing and evaluating a high quality corpus for NLG training.

Keywords

Cite

@article{arxiv.1706.09433,
  title  = {Data-driven Natural Language Generation: Paving the Road to Success},
  author = {Jekaterina Novikova and Ondřej Dušek and Verena Rieser},
  journal= {arXiv preprint arXiv:1706.09433},
  year   = {2017}
}

Comments

WiNLP workshop at ACL 2017

R2 v1 2026-06-22T20:32:35.376Z