ADAPT at SR’20: How Preprocessing and Data Augmentation Help to Improve Surface Realization

Henry Elder


Abstract
In this paper, we describe the ADAPT submission to the Surface Realization Shared Task 2020. We present a neural-based system trained on the English Web Treebank and an augmented dataset, automatically created from existing text corpora.
Anthology ID:
2020.msr-1.3
Volume:
Proceedings of the Third Workshop on Multilingual Surface Realisation
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Anya Belz, Bernd Bohnet, Thiago Castro Ferreira, Yvette Graham, Simon Mille, Leo Wanner
Venue:
MSR
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
30–34
Language:
URL:
https://aclanthology.org/2020.msr-1.3
DOI:
Bibkey:
Cite (ACL):
Henry Elder. 2020. ADAPT at SR’20: How Preprocessing and Data Augmentation Help to Improve Surface Realization. In Proceedings of the Third Workshop on Multilingual Surface Realisation, pages 30–34, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
ADAPT at SR’20: How Preprocessing and Data Augmentation Help to Improve Surface Realization (Elder, MSR 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.msr-1.3.pdf