Prompt-based Learning for Text Readability Assessment

Bruce W. Lee, Jason Lee


Abstract
We propose the novel adaptation of a pre-trained seq2seq model for readability assessment. We prove that a seq2seq model - T5 or BART - can be adapted to discern which text is more difficult from two given texts (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach. Our code is available at github.com/brucewlee/prompt-learning-readability.
Anthology ID:
2023.findings-eacl.135
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1819–1824
Language:
URL:
https://aclanthology.org/2023.findings-eacl.135
DOI:
10.18653/v1/2023.findings-eacl.135
Bibkey:
Cite (ACL):
Bruce W. Lee and Jason Lee. 2023. Prompt-based Learning for Text Readability Assessment. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1819–1824, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Prompt-based Learning for Text Readability Assessment (Lee & Lee, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.135.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.135.mp4