Abstract
In this paper, we propose an end-to-end system for unsupervised text style transfer (UTST). Prior studies on UTST work on the principle of disentanglement between style and content features, which successfully accomplishes the task of generating style-transferred text. The success of a style transfer system depends on three criteria, viz. Style transfer accuracy, Content preservation of source, and Fluency of the generated text. Generated text by disentanglement-based method achieves better style transfer performance but suffers from the lack of content preservation as the previous works suggest. To develop an all-around solution to all three aspects, we use a reinforcement learning-based training objective that gives rewards to the model for generating fluent style transferred text while preserving the source content. On the modeling aspect, we develop a shared encoder and style-specific decoder architecture which uses the Transformer architecture as a backbone. This modeling choice enables us to frame a differentiable back translation objective aiding better content preservation as shown through a careful ablation study. We conclude this paper with both automatic and human evaluation, showing the superiority of our proposed method on sentiment and formality style transfer tasks. Code is available at https://github.com/newcodevelop/Unsupervised-TST.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization. pp. 65–72. Association for Computational Linguistics, Ann Arbor, Michigan (2005). https://aclanthology.org/W05-0909
Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20(1), 37–46 (1960)
Dai, N., Liang, J., Qiu, X., Huang, X.: style transformer: unpaired text style transfer without disentangled latent representation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5997–6007. Association for Computational Linguistics, Florence, Italy (2019). https://doi.org/10.18653/v1/P19-1601. https://aclanthology.org/P19-1601
He, J., Wang, X., Neubig, G., Berg-Kirkpatrick, T.: A probabilistic formulation of unsupervised text style transfer (2020). https://arxiv.org/abs/2002.03912
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017). https://openreview.net/forum?id=rkE3y85ee
Jin, D., Jin, Z., Hu, Z., Vechtomova, O., Mihalcea, R.: Deep learning for text style transfer: a survey. Comput. Linguist. 48(1), 155–205 (2022). https://doi.org/10.1162/coli_a_00426. https://aclanthology.org/2022.cl-1.6
Jing, Y., Yang, Y., Feng, Z., Ye, J., Song, M.: Neural style transfer: a review. CoRR abs/1705.04058 (2017). http://arxiv.org/abs/1705.04058
John, V., Mou, L., Bahuleyan, H., Vechtomova, O.: Disentangled representation learning for non-parallel text style transfer. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 424–434. Association for Computational Linguistics, Florence, Italy (2019). https://doi.org/10.18653/v1/P19-1041. https://aclanthology.org/P19-1041
Li, J., Jia, R., He, H., Liang, P.: Delete, retrieve, generate: a simple approach to sentiment and style transfer. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1865–1874. Association for Computational Linguistics, New Orleans, Louisiana (2018). https://doi.org/10.18653/v1/N18-1169. https://aclanthology.org/N18-1169
Luo, F., et al.: A dual reinforcement learning framework for unsupervised text style transfer. CoRR abs/1905.10060 (2019). http://arxiv.org/abs/1905.10060
Madaan, A., et al.: Politeness transfer: a tag and generate approach. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1869–1881. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.acl-main.169. https://aclanthology.org/2020.acl-main.169
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA (2002). https://doi.org/10.3115/1073083.1073135. https://aclanthology.org/P02-1040
Prabhumoye, S., Quirk, C., Galley, M.: Towards content transfer through grounded text generation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 2622–2632. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https://doi.org/10.18653/v1/N19-1269. https://aclanthology.org/N19-1269
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9(2019)
Rao, S., Tetreault, J.: Dear sir or madam, may I introduce the GYAFC dataset: Corpus, benchmarks and metrics for formality style transfer. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 129–140. Association for Computational Linguistics, New Orleans, Louisiana (2018). https://doi.org/10.18653/v1/N18-1012. https://aclanthology.org/N18-1012
Nogueira dos Santos, C., Melnyk, I., Padhi, I.: Fighting offensive language on social media with unsupervised text style transfer. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 189–194. Association for Computational Linguistics, Melbourne, Australia (2018). https://doi.org/10.18653/v1/P18-2031. https://aclanthology.org/P18-2031
Subramanian, S., Lample, G., Smith, E.M., Denoyer, L., Ranzato, M., Boureau, Y.: Multiple-attribute text style transfer. CoRR abs/1811.00552 (2018). http://arxiv.org/abs/1811.00552
Sudhakar, A., Upadhyay, B., Maheswaran, A.: “Transforming” delete, retrieve, generate approach for controlled text style transfer. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3269–3279. Association for Computational Linguistics, Hong Kong, China (2019). https://doi.org/10.18653/v1/D19-1322. https://aclanthology.org/D19-1322
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, Curran Associates Inc., Red Hook, pp. 6000–6010 (2017)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Xu, J., et al.: Unpaired sentiment-to-sentiment translation: a cycled reinforcement learning approach. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 979–988. Association for Computational Linguistics, Melbourne, Australia (2018). https://doi.org/10.18653/v1/P18-1090. https://aclanthology.org/P18-1090
Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with BERT. CoRR abs/1904.09675 (2019). http://arxiv.org/abs/1904.09675
Zhou, C., et al.: Exploring contextual word-level style relevance for unsupervised style transfer. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7135–7144. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.acl-main.639. https://aclanthology.org/2020.acl-main.639
Acknowledgement
The research reported in this paper is an outcome of the project “HELIOS-Hate, Hyperpartisan, and Hyperpluralism Elicitation and Observer System", sponsored by Wipro.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bandyopadhyay, D., Ekbal, A. (2023). Unsupervised Text Style Transfer Through Differentiable Back Translation and Rewards. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13938. Springer, Cham. https://doi.org/10.1007/978-3-031-33383-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-33383-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33382-8
Online ISBN: 978-3-031-33383-5
eBook Packages: Computer ScienceComputer Science (R0)