Abstract
Text simplification is the process of rewriting a piece of text using simpler vocabulary and grammatical structure in order to make the text more accessible and understandable for a larger audience. In this paper, we introduce a new text simplification model based on the notion of adaptive teaching using a teacher network and a text generation network. We name this new model Simplification via Adaptive Teaching (SAT). Our proposed model sets a new state-of-the-art performance in terms of standard simplification metrics such as SARI and D-SARI with a significant improvement over the previous state of the art on the D-Wikipedia dataset and the Wiki-Doc benchmark dataset. Moreover, we conduct a human evaluation in terms of text simplicity, correctness, and fluency to substantiate SAT’s performance.- Anthology ID:
- 2024.findings-acl.392
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6574–6584
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.392
- DOI:
- Cite (ACL):
- Seyed Ali Bahrainian, Jonathan Dou, and Carsten Eickhoff. 2024. Text Simplification via Adaptive Teaching. In Findings of the Association for Computational Linguistics ACL 2024, pages 6574–6584, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Text Simplification via Adaptive Teaching (Bahrainian et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.392.pdf