E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language

Henry Elder, Sebastian Gehrmann, Alexander O’Connor, Qun Liu


Abstract
In natural language generation (NLG), the task is to generate utterances from a more abstract input, such as structured data. An added challenge is to generate utterances that contain an accurate representation of the input, while reflecting the fluency and variety of human-generated text. In this paper, we report experiments with NLG models that can be used in task oriented dialogue systems. We explore the use of additional input to the model to encourage diversity and control of outputs. While our submission does not rank highly using automated metrics, qualitative investigation of generated utterances suggests the use of additional information in neural network NLG systems to be a promising research direction.
Anthology ID:
W18-6556
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Editors:
Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
457–462
Language:
URL:
https://aclanthology.org/W18-6556
DOI:
10.18653/v1/W18-6556
Bibkey:
Cite (ACL):
Henry Elder, Sebastian Gehrmann, Alexander O’Connor, and Qun Liu. 2018. E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language. In Proceedings of the 11th International Conference on Natural Language Generation, pages 457–462, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language (Elder et al., INLG 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6556.pdf