Position Papers of the 20th Conference on Computer Science and Intelligence Systems

DOI: http://dx.doi.org/10.15439/2025F4661

Citation: Position Papers of the 20th Conference on Computer Science and Intelligence Systems, M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 44, pages 81–86 (2025)

Full text

Abstract. Diachronic text style transfer aims to transform text from one historical period into the style of another while preserving its meaning. However, the scarcity of parallel corpora across time periods makes supervised approaches impractical. In this work, we propose to adapt the CycleGAN architecture, originally developed for unpaired image-to-image translation, to model linguistic change over time. Our method employs a generator and discriminator, both conditioned on temporal information, and trained using a combination of adversarial and cycle-consistency losses. We propose a time-conditioned generative framework that supports both discrete and continuous temporal representations, enabling the model to interpolate between historical language styles. The model is trained on unaligned historical texts and can transform language from any period to another. This approach offers a data-efficient solution for diachronic language modeling and opens new research directions in historical linguistics, digital humanities, and unsupervised style transfer.

References

1. J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks,” in 2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, Oct. 2017. https://dx.doi.org/10.1109/ICCV.2017.244. ISBN 978-1-5386-1032-9 pp. 2242–2251. [Online]. Available: http://ieeexplore.ieee.org/document/8237506/
2. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative Adversarial Networks,” Jun. 2014, https://arxiv.org/abs/1406.2661 [stat]. [Online]. Available: http://arxiv.org/abs/1406.2661
3. Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo, “StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE, Jun. 2018. https://dx.doi.org/10.1109/CVPR.2018.00916. ISBN 978-1-5386-6420-9 pp. 8789–8797. [Online]. Available: https://ieeexplore.ieee.org/document/8579014/
4. Y. Huang, W. Zhu, D. Xiong, Y. Zhang, C. Hu, and F. Xu, “Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer,” in Proceedings of the 28th International Conference on Computational Linguistics, D. Scott, N. Bel, and C. Zong, Eds. Barcelona, Spain (Online): International Committee on Computational Linguistics, Dec. 2020. https://dx.doi.org/10.18653/v1/2020.coling-main.201 pp. 2213–2223. [Online]. Available: https://aclanthology.org/2020.coling-main.201/
5. M. Lorandi, A. Mohamed, and K. McGuinness, “Adapting the CycleGAN architecture for text style transfer.” Galway, Ireland: Zenodo, Aug. 2023. https://dx.doi.org/10.5281/zenodo.8268838. [Online]. Available: https://doi.org/10.5281/zenodo.8268838
6. H. Wang, Y. Lepage, and C. L. Goh, “Unpaired Abstract-to-Conclusion Text Style Transfer using CycleGANs,” in 2020 International Conference on Advanced Computer Science and Information Systems (ICACSIS). Depok, Indonesia: IEEE, Oct. 2020. https://dx.doi.org/10.1109/ICAC-SIS51025.2020.9263246. ISBN 978-1-7281-9279-6 pp. 435–440. [Online]. Available: https://ieeexplore.ieee.org/document/9263246/
7. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is All you Need,” in Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html