Skip to main content
DORAS
DCU Online Research Access Service
Login (DCU Staff Only)
How to make neural natural language generation as reliable as templates in task-oriented dialogue

Elder, Henry, O'Connor, Alexander ORCID: 0000-0003-0301-999X and Foster, Jennifer ORCID: 0000-0002-7789-4853 (2020) How to make neural natural language generation as reliable as templates in task-oriented dialogue. In: 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 16-20 Nov 2020, Online.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB

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.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Computational linguistics
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). . Association for Computational Linguistics (ACL).
Publisher:Association for Computational Linguistics (ACL)
Official URL:http://dx.doi.org/10.18653/v1/2020.emnlp-main.230
Copyright Information:2020 Association for Computational Linguistics. (CC-BY-4.0)
Funders:Science Foundation Ireland via ADAPT Centre for Digital Content Technology is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund
ID Code:25957
Deposited On:02 Jun 2021 15:21 by Jennifer Foster . Last Modified 02 Jun 2021 15:21

Downloads

Downloads per month over past year

Archive Staff Only: edit this record

Altmetric
- Altmetric
+ Altmetric
  • Student Email
  • Staff Email
  • Student Apps
  • Staff Apps
  • Loop
  • Disclaimer
  • Privacy
  • Contact Us