Document-Level Planning for Text Simplification

Liam Cripwell, Joël Legrand, Claire Gardent


Abstract
Most existing work on text simplification is limited to sentence-level inputs, with attempts to iteratively apply these approaches to document-level simplification failing to coherently preserve the discourse structure of the document. We hypothesise that by providing a high-level view of the target document, a simplification plan might help to guide generation. Building upon previous work on controlled, sentence-level simplification, we view a plan as a sequence of labels, each describing one of four sentence-level simplification operations (copy, rephrase, split, or delete). We propose a planning model that labels each sentence in the input document while considering both its context (a window of surrounding sentences) and its internal structure (a token-level representation). Experiments on two simplification benchmarks (Newsela-auto and Wiki-auto) show that our model outperforms strong baselines both on the planning task and when used to guide document-level simplification models.
Anthology ID:
2023.eacl-main.70
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
993–1006
Language:
URL:
https://aclanthology.org/2023.eacl-main.70
DOI:
10.18653/v1/2023.eacl-main.70
Bibkey:
Cite (ACL):
Liam Cripwell, Joël Legrand, and Claire Gardent. 2023. Document-Level Planning for Text Simplification. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 993–1006, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Document-Level Planning for Text Simplification (Cripwell et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.70.pdf
Video:
 https://aclanthology.org/2023.eacl-main.70.mp4