The DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.
Style Transfer Through Back-Translation
Open accessAbstract
Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context.This paper introduces a new method for automatic style transfer.We first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties.Then adversarial generation techniques are used to make the output match the desired style.We evaluate this technique on three different style transformations: sentiment, gender and political slant.Compared to two state-of-the-art style transfer modeling techniques we show improvements both in automatic evaluation of style transfer and in manual evaluation of meaning preservation and fluency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Self-citationMoses: open source toolkit for statistical machine translation
Koehn, P., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., et al. (2007) · Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions - ACL '07 · doi:10.3115/1557769.1557821 · Cited by 4,735 · cited 1×
“Data were tokenized using the Moses tokenizer (Koehn et al., 2007).”
MethodGet To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775
Stereotype Threat and Women's Math Performance
Spencer, S. J., Steele, C. M., & Quinn, D. M. (1999) · Journal of Experimental Social Psychology · doi:10.1006/jesp.1998.1373 · Cited by 3,435
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F. B., WATTENBERG, M. P., Corrado, G. S., et al. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00065 · Cited by 1,941
Vinyals, O., & Le, Q. (2015) · arXiv · doi:10.48550/arxiv.1506.05869 · Cited by 1,400
Research works printed but not linked: 9
- Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised neural ma- chine translation. In Proc ICLR.
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In Proc. ICLR.
- Junbo, Zhao, Y. Kim, K. Zhang, A. M. Rush, and Y. LeCun. 2017. Adversarially Regularized Autoen- coders for Generating Discrete Structures. ArXiv e- prints.
- Andrej Karpathy and Li Fei-Fei. 2015. Deep visual- semantic alignments for generating image descrip- tions. In Proc. CVPR, pages 3128-3137.
- Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc'Aurelio Ranzato. 2018. Unsupervised machine translation using monolingual corpora only. In Proc. ICLR.
- J. Li, R. Jia, H. He, and P. Liang. 2018. Delete, Re- trieve, Generate: A Simple Approach to Sentiment and Style Transfer. ArXiv e-prints.
- Dong Nguyen, A. Seza Dogruöz, Carolyn P. Rosé, and Franciska de Jong. 2016. Computational soci- olinguistics: A survey. Computational Linguistics, 42(3):537-593.
- Oriol Vinyals and Quoc Le. 2015. A neural conversa- tional model. In Proc. ICML Deep Learning Work- shop.
- Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A network- based end-to-end trainable task-oriented dialogue system. In Proc. EACL.
Cited by
Sorted by citations
Items 301–346 of 346
Monolingual and Cross-lingual Zero-shot Style TransferPreprint
Korotkova, E., Del, M., & Fishel, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.00179 · Cited by 1
Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement LearningPreprint
Xu, P., Wu, C.-S., Madotto, A., & Fung, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03582 · Cited by 8
Semi-supervised Text Style Transfer: Cross Projection in Latent SpacePreprint
Shang, M., Li, P., Fu, Z., Bing, L., Zhao, D., Shi, S., & Yan, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11493 · Cited by 7
Learning deep models via optimal transport distance
Chen, L. (2021) · Cited by 1
Time-Aware Ancient Chinese Text Translation and InferencePreprint
Chang, E., Shiue, Y.-T., Yeh, H.-S., & Demberg, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03179 · Cited by 1
QuaSE: Accurate Text Style Transfer under Quantifiable GuidancePreprint
Liao, Y., Bing, L., Li, P., Shi, S., Lam, W. P., & Zhang, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.07007
Massive Styles Transfer with Limited Labeled DataPreprint
Zang, H., & Wan, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00580
Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutPreprint
Tan, H. X., Yu, L., & Bansal, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04195
Kang, D., Gangal, V., & Hovy, E. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00098
Generating summaries tailored to target characteristicsPreprint
Chawla, K., Singh, H., Pramanik, A., Kumar, M., & Srinivasan, B. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.08492
Doran, C. (2019) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.17139893
Reflection-based Word Attribute TransferPreprint
Ishibashi, Y., Sudoh, K., Yoshino, K., & Nakamura, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02598
Unpaired Abstract-to-Conclusion Text Style Transfer using CycleGANs
Wang, H., Lepage, Y., & Goh, C. L. (2020) · International Conference on Advanced Computer Science and Information Systems · doi:10.1109/icacsis51025.2020.9263246
Empirical Evaluation of Supervision Signals for Style Transfer ModelsPreprint
Puzikov, Y., Stanley, S., Gurevych, I., & Schweizer, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06172
User Behavior Set: Medley of User Behaviors to Eliminate Data Spatio-Temporal Sparsity
Huang, Y., Hu, X., Lian, J., & Jiang, X. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1802/3/032037
Aligning the training and evaluation of unsupervised text style Transfer
Qian, W., Zhu, F., Yang, J., Han, J., & Hu, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414515
Unsupervised Text Style Transfer via an Enhanced Operation Pipeline
Qian, W., Yang, J., Zhu, F., Su, Y., & Hu, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77964-1_9
PGST: a Polyglot Gender Style Transfer methodPreprint
Khanmohammadi, R., & Mirroshandel, S. A. (2020) · arXiv (Cornell University) · doi:10.13140/rg.2.2.29307.64807
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted RestylingPreprint
Riley, P., Constant, N., Guo, M., Kumar, G., Uthus, D., & Parekh, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03802 · Cited by 17
Denoising AutoEncoder Based Delete and Generate Approach for Text Style Transfer
Hu, T., Yang, H., & Meinel, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86365-4_4
Text Simplification for Comprehension-based Question-AnsweringPreprint
Dadu, T., Pant, K., Nagar, S., Barbhuiya, F. A., & Dey, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13984
Contrapositive Local Class Inference
Kashefi, O., & Hwa, R. (2021) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2021.wnut-1.41
Non-Parallel Text Style Transfer using Self-Attentional Discriminator as Supervisor
Feng, K., Zhu, Y., & Yu, J. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671820
Nishimura, R., Mori, R., Ohta, K., & Kitaoka, N. (2022) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.37-3_ids-f
Kagawa, R., Baba, Y., & Tsurushima, H. (2020) · doi:10.2196/preprints.24790
Latent Constraints on Unsupervised Text-Graph Alignment with Information Asymmetry
Tian, J., Chen, W., Li, Y., Fan, C., He, H., & Jin, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26600
Cho, H., Kim, D., Ryu, S., Park, C., Noh, H., Hwang, J.-I., Choi, M., Choi, E., & Choo, J. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.366
PGST: A Persian gender style transfer method
Khanmohammadi, R., & Mirroshandel, S. A. (2023) · Natural Language Engineering · doi:10.1017/s1351324923000426 · Cited by 1
FASST: Few-Shot Abstractive Summarization for Style Transfer
Alsayed, O., Muncy, C., Youssef, A., & Green, R. J. (2023) · doi:10.1109/icnlp58431.2023.00045
Qu, Q., Wang, J., Yang, K., Zhang, H., & Lv, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44699-3_1
“Slow Service” ↛ “Great Food”: Enhancing Content Preservation in Unsupervised Text Style Transfer
Zhu, W., & Bhat, S. (2022) · International Conference on Natural Language Generation · doi:10.18653/v1/2022.inlg-main.3
Text Style Transfer: A Comprehensive Study on Methodologies and Evaluation
Parekh, N., Trivedi, S., & Srivastava, K. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-3481-2_22
Balepur, N., Huang, J., & Chang, K. C. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.288 · Cited by 1
Translating away Translationese without Parallel Data
Jalota, R., Chowdhury, K. D., España-Bonet, C., & van Genabith, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.438 · Cited by 3
Memory-enhanced text style transfer with dynamic style learning and calibration
Lin, F., Song, Y., Tian, Z., Chen, W., Dong, D., & Liu, B. (2024) · Science China Information Sciences · doi:10.1007/s11432-022-3726-0
Reframing social media discourse: Converting hate speech to non-hate speech
Kostiuk, Y., Tonja, A. L., Sidorov, G., & Kolesnikova, O. (2024) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-219348 · Cited by 4
Toward Unbiased High-Quality Portraits through Latent-Space Evaluation
Almhaithawi, D., Bellini, A., & Cerquitelli, T. (2024) · Journal of Imaging · doi:10.3390/jimaging10070157
THE BAT: Thoughts Hierarchical Enhancement Beyond Arbitrary Text Style Transfer
Zeng, B., Liang, J., Hua, Y., Li, R., Deng, H., Peng, Y., & Wang, R. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5672-8_32
Kumar, M. P., Hadassah, B. S., & Lokesh, D. (2025) · ITM Web of Conferences · doi:10.1051/itmconf/20257401017
TSTBench: A Comprehensive Benchmark for Text Style Transfer
Xie, Y., Gui, J., Che, Z., Zhu, L., Hu, Y., & Pan, Z. (2025) · Entropy · doi:10.3390/e27060575
A semi supervised framework for human and machine collaboration in computer assisted text refinement
Sun, Y., Wang, Y., Yang, H., & Suen, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-10085-z
Exploring Large Language Models for Data Augmentation: A Case Study for Text Style Transfer
Toshevska, M., Mirceva, G., & Gievska, S. (2025) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro65660.2025.11131729
Dialogue Evaluation Is Affected by How Raters Perceive Stylistic Similarity
Numaya, I., Moriya, S., Sato, S., Akama, R., & Suzuki, J. (2025) · Journal of Natural Language Processing · doi:10.5715/jnlp.32.1241
Analysis and control of online interactions through neural natural language processing
Laugier, L. (2022) · theses.fr (ABES) · doi:10.70675/4743aa15z209az4addz8f29z95150aa230b8
CSPC: A High-Quality Dataset And Comprehensive Evaluation Metric For Chinese Sentence Paraphrasing
Lin, H., Xiong, Z., Zhan, S., Li, Y., Zheng, H.-T., Yu, Y., Kim, H.-G., & Yang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461619
Metadata
- Authors
- Prabhumoye, S., Tsvetkov, Y., Salakhutdinov, R., & Black, A. W.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2018
- Pages
- 866-876
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2798651744
- Cited by
- 348
- References
- 41
- Citations by year
- 2026: 4 · 2025: 12 · 2024: 12 · 2023: 41 · 2022: 51 · 2021: 64 · 2020: 71 · 2019: 82 · 2018: 10
- FWCI
- 17.11
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1526745)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- style transfer, back-translation, sentiment transfer, meaning preservation, fluency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
