STEER: Unified Style Transfer with Expert Reinforcement

Skyler Hallinan, Faeze Brahman, Ximing Lu, Jaehun Jung, Sean Welleck, Yejin Choi


Abstract
While text style transfer has many applications across natural language processing, the core premise of transferring from a single source style is unrealistic in a real-world setting. In this work, we focus on arbitrary style transfer: rewriting a text from an arbitrary, unknown style to a target style. We propose STEER: Unified Style Transfer with Expert Reinforcement, a unified frame-work developed to overcome the challenge of limited parallel data for style transfer. STEER involves automatically generating a corpus of style-transfer pairs using a product of experts during decoding. The generated offline data is then used to pre-train an initial policy before switching to online, off-policy reinforcement learning for further improvements via fine-grained reward signals. STEER is unified and can transfer to multiple target styles from an arbitrary, unknown source style, making it particularly flexible and efficient. Experimental results on a challenging dataset with text from a diverse set of styles demonstrate state-of-the-art results compared to competitive baselines. Remarkably, STEER outperforms the 175B parameter instruction-tuned GPT-3 on overall style transfer quality, despite being 226 times smaller in size. We also show STEER is robust, maintaining its style transfer capabilities on out-of-domain data, and surpassing nearly all baselines across various styles. The success of our method highlights the potential of RL algorithms when augmented with controllable decoding to overcome the challenge of limited data supervision.
Anthology ID:
2023.findings-emnlp.506
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:
7546–7562
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.506
DOI:
10.18653/v1/2023.findings-emnlp.506
Bibkey:
Cite (ACL):
Skyler Hallinan, Faeze Brahman, Ximing Lu, Jaehun Jung, Sean Welleck, and Yejin Choi. 2023. STEER: Unified Style Transfer with Expert Reinforcement. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7546–7562, Singapore. Association for Computational Linguistics.
Cite (Informal):
STEER: Unified Style Transfer with Expert Reinforcement (Hallinan et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.506.pdf