Edit-Constrained Decoding for Sentence Simplification

Tatsuya Zetsu, Yuki Arase, Tomoyuki Kajiwara


Abstract
We propose edit operation based lexically constrained decoding for sentence simplification. In sentence simplification, lexical paraphrasing is one of the primary procedures for rewriting complex sentences into simpler correspondences. While previous studies have confirmed the efficacy of lexically constrained decoding on this task, their constraints can be loose and may lead to sub-optimal generation. We address this problem by designing constraints that replicate the edit operations conducted in simplification and defining stricter satisfaction conditions. Our experiments indicate that the proposed method consistently outperforms the previous studies on three English simplification corpora commonly used in this task.
Anthology ID:
2024.findings-emnlp.419
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7161–7173
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.419
DOI:
Bibkey:
Cite (ACL):
Tatsuya Zetsu, Yuki Arase, and Tomoyuki Kajiwara. 2024. Edit-Constrained Decoding for Sentence Simplification. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7161–7173, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Edit-Constrained Decoding for Sentence Simplification (Zetsu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.419.pdf