Improving Quality and Efficiency in Plan-based Neural Data-to-text Generation

Amit Moryossef, Yoav Goldberg, Ido Dagan


Abstract
We follow the step-by-step approach to neural data-to-text generation proposed by Moryossef et al (2019), in which the generation process is divided into a text planning stage followed by a plan realization stage. We suggest four extensions to that framework: (1) we introduce a trainable neural planning component that can generate effective plans several orders of magnitude faster than the original planner; (2) we incorporate typing hints that improve the model’s ability to deal with unseen relations and entities; (3) we introduce a verification-by-reranking stage that substantially improves the faithfulness of the resulting texts; (4) we incorporate a simple but effective referring expression generation module. These extensions result in a generation process that is faster, more fluent, and more accurate.
Anthology ID:
W19-8645
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
377–382
Language:
URL:
https://aclanthology.org/W19-8645
DOI:
10.18653/v1/W19-8645
Bibkey:
Cite (ACL):
Amit Moryossef, Yoav Goldberg, and Ido Dagan. 2019. Improving Quality and Efficiency in Plan-based Neural Data-to-text Generation. In Proceedings of the 12th International Conference on Natural Language Generation, pages 377–382, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Improving Quality and Efficiency in Plan-based Neural Data-to-text Generation (Moryossef et al., INLG 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/W19-8645.pdf
Supplementary attachment:
 W19-8645.Supplementary_Attachment.pdf