PromptARA: Improving Deep Representation in Hybrid Automatic Readability Assessment with Prompt and Orthogonal Projection

Jinshan Zeng, Xianglong Yu, Xianchao Tong, Wenyan Xiao


Abstract
Readability assessment aims to automatically classify texts based on readers’ reading levels. The hybrid automatic readability assessment (ARA) models using both deep and linguistic features have attracted rising attention in recent years due to their impressive performance. However, deep features are not fully explored due to the scarcity of training data, and the fusion of deep and linguistic features is not very effective in existing hybrid ARA models. In this paper, we propose a novel hybrid ARA model called PromptARA through employing prompts to improve deep feature representations and an orthogonal projection layer to fuse both deep and linguistic features. A series of experiments are conducted over four English and two Chinese corpora to show the effectiveness of the proposed model. Experimental results demonstrate that the proposed model is superior to state-of-the-art models.
Anthology ID:
2023.findings-emnlp.1025
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15360–15371
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.1025
DOI:
10.18653/v1/2023.findings-emnlp.1025
Bibkey:
Cite (ACL):
Jinshan Zeng, Xianglong Yu, Xianchao Tong, and Wenyan Xiao. 2023. PromptARA: Improving Deep Representation in Hybrid Automatic Readability Assessment with Prompt and Orthogonal Projection. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15360–15371, Singapore. Association for Computational Linguistics.
Cite (Informal):
PromptARA: Improving Deep Representation in Hybrid Automatic Readability Assessment with Prompt and Orthogonal Projection (Zeng et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.1025.pdf