Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text

Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst


Abstract
This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (k-SCST), in which the model proposes several candidate simplifications, computes each candidate’s reward, and encourages candidates that outperform the mean reward. Finally, we propose a realistic text comprehension task as an evaluation method for text simplification. When tested on the English news domain, the KiS model outperforms strong supervised baselines by more than 4 SARI points, and can help people complete a comprehension task an average of 18% faster while retaining accuracy, when compared to the original text.
Anthology ID:
2021.acl-long.498
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6365–6378
Language:
URL:
https://aclanthology.org/2021.acl-long.498
DOI:
10.18653/v1/2021.acl-long.498
Bibkey:
Cite (ACL):
Philippe Laban, Tobias Schnabel, Paul Bennett, and Marti A. Hearst. 2021. Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6365–6378, Online. Association for Computational Linguistics.
Cite (Informal):
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text (Laban et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.498.pdf
Video:
 https://aclanthology.org/2021.acl-long.498.mp4
Code
 tingofurro/keep_it_simple
Data
NewselaWikiLarge