Controllable Text Simplification with Deep Reinforcement Learning

Daiki Yanamoto, Tomoki Ikawa, Tomoyuki Kajiwara, Takashi Ninomiya, Satoru Uchida, Yuki Arase

Abstract
We propose a method for controlling the difficulty of a sentence based on deep reinforcement learning. Although existing models are trained based on the word-level difficulty, the sentence-level difficulty has not been taken into account in the loss function. Our proposed method generates sentences of appropriate difficulty for the target audience through reinforcement learning using a reward calculated based on the difference between the difficulty of the output sentence and the target difficulty. Experimental results of English text simplification show that the proposed method achieves a higher performance than existing approaches. Compared to previous studies, the proposed method can generate sentences whose grade-levels are closer to those of human references estimated using a fine-tuned pre-trained model.
Anthology ID:
2022.aacl-short.49
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
398–404
Language:
URL:
https://aclanthology.org/2022.aacl-short.49
DOI:
Bibkey:
Cite (ACL):
Daiki Yanamoto, Tomoki Ikawa, Tomoyuki Kajiwara, Takashi Ninomiya, Satoru Uchida, and Yuki Arase. 2022. Controllable Text Simplification with Deep Reinforcement Learning. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 398–404, Online only. Association for Computational Linguistics.
Cite (Informal):
Controllable Text Simplification with Deep Reinforcement Learning (Yanamoto et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2022.aacl-short.49.pdf
PDF Search