How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue

Henry Elder, Alexander O’Connor, Jennifer Foster


Abstract
Neural Natural Language Generation (NLG) systems are well known for their unreliability. To overcome this issue, we propose a data augmentation approach which allows us to restrict the output of a network and guarantee reliability. While this restriction means generation will be less diverse than if randomly sampled, we include experiments that demonstrate the tendency of existing neural generation approaches to produce dull and repetitive text, and we argue that reliability is more important than diversity for this task. The system trained using this approach scored 100% in semantic accuracy on the E2E NLG Challenge dataset, the same as a template system.
Anthology ID:
2020.emnlp-main.230
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2877–2888
Language:
URL:
https://aclanthology.org/2020.emnlp-main.230
DOI:
10.18653/v1/2020.emnlp-main.230
Bibkey:
Cite (ACL):
Henry Elder, Alexander O’Connor, and Jennifer Foster. 2020. How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2877–2888, Online. Association for Computational Linguistics.
Cite (Informal):
How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue (Elder et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.230.pdf
Video:
 https://slideslive.com/38939317