Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression

Jinshan Zeng; Yudong Xie; Xianglong Yu; John S. Y. Lee; Ding-Xuan Zhou

Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression

Jinshan Zeng, Yudong Xie, Xianglong Yu, John S. Y. Lee, Ding-Xuan Zhou

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

10 Citations (Scopus)

116 Downloads (CityUHK Scholars)

Abstract

The readability assessment task aims to assign a difficulty grade to a text. While neural models have recently demonstrated impressive performance, most do not exploit the ordinal nature of the difficulty grades, and make little effort for model initialization to facilitate fine-tuning. We address these limitations with soft labels for ordinal regression, and with model pre-training through prediction of pairwise relative text difficulty. We incorporate these two components into a model based on hierarchical attention networks, and evaluate its performance on both English and Chinese datasets. Experimental results show that our proposed model outperforms competitive neural models and statistical classifiers on most datasets.

Original language	English
Title of host publication	Findings of the Association for Computational Linguistics
Subtitle of host publication	EMNLP 2022
Editors	Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Publisher	Association for Computational Linguistics
Pages	4586-4597
Publication status	Published - Dec 2022
Event	2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) - Hybrid, Abu Dhabi, United Arab Emirates Duration: 7 Dec 2022 → 11 Dec 2022 https://2022.emnlp.org/

Conference

Conference	2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	7/12/22 → 11/12/22
Internet address	https://2022.emnlp.org/

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

135127738.pdfFinal Published version, 826 KBLicence: CC BY

https://aclanthology.org/2022.findings-emnlp.334

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zeng, J., Xie, Y., Yu, X., Lee, J. S. Y., & Zhou, D.-X. (2022). Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression. In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2022 (pp. 4586-4597). Association for Computational Linguistics. https://aclanthology.org/2022.findings-emnlp.334

@inproceedings{c22966c51d8c4ec692afaeef6f9b1e10,

title = "Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression",

abstract = "The readability assessment task aims to assign a difficulty grade to a text. While neural models have recently demonstrated impressive performance, most do not exploit the ordinal nature of the difficulty grades, and make little effort for model initialization to facilitate fine-tuning. We address these limitations with soft labels for ordinal regression, and with model pre-training through prediction of pairwise relative text difficulty. We incorporate these two components into a model based on hierarchical attention networks, and evaluate its performance on both English and Chinese datasets. Experimental results show that our proposed model outperforms competitive neural models and statistical classifiers on most datasets.",

author = "Jinshan Zeng and Yudong Xie and Xianglong Yu and Lee, {John S. Y.} and Ding-Xuan Zhou",

year = "2022",

month = dec,

language = "English",

pages = "4586--4597",

editor = "Goldberg, {Yoav } and Zornitsa Kozareva and Yue Zhang",

booktitle = "Findings of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) ; Conference date: 07-12-2022 Through 11-12-2022",

url = "https://2022.emnlp.org/",

}

Zeng, J, Xie, Y, Yu, X, Lee, JSY & Zhou, D-X 2022, Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression. in Y Goldberg, Z Kozareva & Y Zhang (eds), Findings of the Association for Computational Linguistics: EMNLP 2022. Association for Computational Linguistics, pp. 4586-4597, 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), Abu Dhabi, United Arab Emirates, 7/12/22. <https://aclanthology.org/2022.findings-emnlp.334>

Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression. / Zeng, Jinshan; Xie, Yudong; Yu, Xianglong et al.
Findings of the Association for Computational Linguistics: EMNLP 2022. ed. / Yoav Goldberg; Zornitsa Kozareva; Yue Zhang. Association for Computational Linguistics, 2022. p. 4586-4597.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression

AU - Zeng, Jinshan

AU - Xie, Yudong

AU - Yu, Xianglong

AU - Lee, John S. Y.

AU - Zhou, Ding-Xuan

PY - 2022/12

Y1 - 2022/12

N2 - The readability assessment task aims to assign a difficulty grade to a text. While neural models have recently demonstrated impressive performance, most do not exploit the ordinal nature of the difficulty grades, and make little effort for model initialization to facilitate fine-tuning. We address these limitations with soft labels for ordinal regression, and with model pre-training through prediction of pairwise relative text difficulty. We incorporate these two components into a model based on hierarchical attention networks, and evaluate its performance on both English and Chinese datasets. Experimental results show that our proposed model outperforms competitive neural models and statistical classifiers on most datasets.

AB - The readability assessment task aims to assign a difficulty grade to a text. While neural models have recently demonstrated impressive performance, most do not exploit the ordinal nature of the difficulty grades, and make little effort for model initialization to facilitate fine-tuning. We address these limitations with soft labels for ordinal regression, and with model pre-training through prediction of pairwise relative text difficulty. We incorporate these two components into a model based on hierarchical attention networks, and evaluate its performance on both English and Chinese datasets. Experimental results show that our proposed model outperforms competitive neural models and statistical classifiers on most datasets.

UR - http://www.scopus.com/inward/record.url?scp=85149850339&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85149850339&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SP - 4586

EP - 4597

BT - Findings of the Association for Computational Linguistics

A2 - Goldberg, Yoav

A2 - Kozareva, Zornitsa

A2 - Zhang, Yue

PB - Association for Computational Linguistics

T2 - 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

Y2 - 7 December 2022 through 11 December 2022

ER -

Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression

Abstract

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this