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.
@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}
}