Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features

Bruce W. Lee, Yoo Sung Jang, Jason Lee


Abstract
We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we explore suitable transformers and traditional ML models. Then, we extract 255 handcrafted linguistic features using self-developed extraction software. Finally, we assemble those to create several hybrid models, achieving state-of-the-art (SOTA) accuracy on popular datasets in readability assessment. The use of handcrafted features help model performance on smaller datasets. Notably, our RoBERTA-RF-T1 hybrid achieves the near-perfect classification accuracy of 99%, a 20.3% increase from the previous SOTA.
Anthology ID:
2021.emnlp-main.834
Original:
2021.emnlp-main.834v1
Version 2:
2021.emnlp-main.834v2
Version 3:
2021.emnlp-main.834v3
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10669–10686
Language:
URL:
https://aclanthology.org/2021.emnlp-main.834
DOI:
10.18653/v1/2021.emnlp-main.834
Bibkey:
Cite (ACL):
Bruce W. Lee, Yoo Sung Jang, and Jason Lee. 2021. Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10669–10686, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features (Lee et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.834.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.834.mp4
Code
 brucewlee/lingfeat
Data
OneStopEnglish