Reformulating Unsupervised Style Transfer as Paraphrase Generation

What it is about

The method, STRAP, treats style transfer as paraphrase generation. A diverse paraphrase model turns sentences from every style into neutral paraphrases, which gives pseudo-parallel data. For each style, an inverse paraphraser (a fine-tuned GPT-2) maps a paraphrase back into that style. No reinforcement learning, variational inference or sampling during training is needed. On formality transfer and Shakespeare imitation it beats prior unsupervised systems by 2 to 3 times on automatic scores and 4 to 5 times on human scores. The survey of 23 style-transfer papers finds that only three aggregate their metrics per sentence; a naive baseline that copies or samples a random target sentence scores well under corpus-level averaging. The paper therefore proposes a sentence-level joint score, a geometric mean of style accuracy, similarity and fluency. It also releases a 15M-sentence dataset in 11 styles.

Ideas

I1. Sentence-level joint score. In normal mode, combine exact match, chrF and the divergence class per sentence before averaging, and report a copy baseline and a random-verse baseline in every table. A system that does not beat both is not reported as progress.
I2. Paraphrase-as-noise for deltas. Translate each verse to the standard and back through the meta-world, which yields neutral-to-author pairs, then learn a per-author inverse table from those pairs as counts (most frequent chunk in the most specific context). The neural inverse model is not for Mova; the counted inverse is.
I3. Ablation of the pseudo-pairs. Remove the paraphrase-as-noise step and measure the loss on dev, reporting it in the value-ablation format before any claim.

For Mova

The sentence-level joint score and the baselines belong in tools/translate/measure.rs. The paraphrase-as-noise idea touches profile.rs and open problem 6 (weighting corpora). The paper's GPT-2 models are teachers at most; the rules in Mova stay count-based and deterministic.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.emnlp-main.55

@inproceedings{krishna2020reformulating,
  title = {{Reformulating Unsupervised Style Transfer as Paraphrase Generation}},
  author = {Krishna, Kalpesh and Wieting, John and Iyyer, Mohit},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.55},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.55}
}

References

103 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

Eneko Agirre, Carmen Banea, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Rada Mihalcea, German Rigau, and Janyce Wiebe. 2016. SemEval-2016 task 1: Semantic textual similarity, monolingual and cross-lingual evaluation. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). find
Nader Akoury, Kalpesh Krishna, and Mohit Iyyer. 2019. Syntactically supervised transformers for faster neural machine translation. In Proceedings of the Association for Computational Linguistics. find
Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein generative adversarial networks. In Proceedings of the International Conference of Machine Learning. find
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations. find
Rahul Bhagat and Eduard Hovy. 2013. Squibs: What is a paraphrase? Computational Linguistics, 39(3):463–472. find
Su Lin Blodgett, Lisa Green, and Brendan O’Connor. 2016. Demographic dialectal variation in social media: A case study of African-American English. In Proceedings of Empirical Methods in Natural Language Processing. Association for Computational Linguistics. find
Ondřej Bojar, Ondřej Dušek, Tom Kocmi, Jindřich Libovický, Michal Novák, Martin Popel, Roman Sudarikov, and Dušan Variš. 2016. CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered. In Text, Speech, and Dialogue: 19th International Conference, TSD 2016, number 9924 in Lecture Notes in Computer Science, pages 231–238, Cham / Heidelberg / New York / Dordrecht / London. Masaryk University, Springer International Publishing. find
Samuel Bowman, Luke Vilnis, Oriol Vinyals, Andrew Dai, Rafal Jozefowicz, and Samy Bengio. 2016. Generating sentences from a continuous space. In Conference on Computational Natural Language Learning. find
Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. Re-evaluating the role of Bleu in machine translation research. In Proceedings of the European Chapter of the Association for Computational Linguistics. find
Mingda Chen, Qingming Tang, Sam Wiseman, and Kevin Gimpel. 2019. Controllable paraphrase generation with a syntactic exemplar. In Proceedings of the Association for Computational Linguistics, Florence, Italy. Association for Computational Linguistics. find
Ning Dai, Jianze Liang, Xipeng Qiu, and Xuanjing Huang. 2019. Style transformer: Unpaired text style transfer without disentangled latent representation. In Proceedings of the Association for Computational Linguistics. find
Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: a simple approach to controlled text generation. In Proceedings of the International Conference on Learning Representations. find
Mark Davies. 2012. Expanding horizons in historical linguistics with the 400-million word corpus of historical american english. Corpora. find
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Conference of the North American Chapter of the Association for Computational Linguistics, pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. find
Chrysanne DiMarco and Graeme Hirst. 1993. A computational theory of goal-directed style in syntax. Computational Linguistics, 19(3):451–499. find
Penelope Eckert. 2008. Variation and the indexical field 1. Journal of sociolinguistics, 12(4). find
Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5):378. find
Markus Freitag, David Grangier, and Isaac Caswell. 2020. Bleu might be guilty but references are not innocent. arXiv preprint arXiv:2004.06063. ↗
Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2018. Style transfer in text: Exploration and evaluation. In Association for the Advancement of Artificial Intelligence. find
John J Godfrey, Edward C Holliman, and Jane Mc-Daniel. 1992. Switchboard: Telephone speech corpus for research and development. In IEEE International Conference on Acoustics, Speech, and Signal Processing. find
Tanya Goyal and Greg Durrett. 2020. Neural syntactic preordering for controlled paraphrase generation. Proceedings of the Association for Computational Linguistics. find
Stephen J Green and Chrysanne DiMarco. 1993. Stylistic decision-making in natural language generation. In European Workshop on Trends in Natural Language Generation, pages 125–143. Springer. find
Tommi Gröndahl and N Asokan. 2019. Effective writing style imitation via combinatorial paraphrasing. arXiv preprint arXiv:1905.13464. ↗
Ankush Gupta, Arvind Agarwal, Prawaan Singh, and Piyush Rai. 2018. A deep generative framework for paraphrase generation. In Association for the Advancement of Artificial Intelligence. find
Kelvin Guu, Tatsunori B Hashimoto, Yonatan Oren, and Percy Liang. 2018. Generating sentences by editing prototypes. Transactions of the Association for Computational Linguistics. find
Michael Hart. 1992. The history and philosophy of Project Gutenberg. Project Gutenberg. find
Junxian He, Xinyi Wang, Graham Neubig, and Taylor Berg-Kirkpatrick. 2020. A probabilistic formulation of unsupervised text style transfer. In Proceedings of the International Conference on Learning Representations. find
George Heidorn. 2000. Intelligent writing assistance. Handbook of natural language processing, pages 181–207. find
Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, and David Meger. 2018. Deep reinforcement learning that matters. In Association for the Advancement of Artificial Intelligence. find
Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In Proceedings of the International Conference on Learning Representations. find
Melvin Johnson, Mike Schuster, Quoc V Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, et al. 2017. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics. find
Jad Kabbara and Jackie Chi Kit Cheung. 2016. Stylistic transfer in natural language generation systems using recurrent neural networks. In Proceedings of the Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods. find
Daniel Kahneman. 2011. Macmillan. Thinking, fast and slow. find
Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361. ↗
Divyansh Kaushik, Eduard Hovy, and Zachary C Lipton. 2020. Learning the difference that makes a difference with counterfactually-augmented data. In Proceedings of the International Conference on Learning Representations. find
Maurice G Kendall. 1938. A new measure of rank correlation. Biometrika, 30(1/2):81–93. find
Nitish Shirish Keskar, Bryan McCann, Lav R Varshney, Caiming Xiong, and Richard Socher. 2019. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858. ↗
Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of Empirical Methods in Natural Language Processing. find
Eduard Hovy. 1987. Generating natural language under pragmatic constraints. Journal of Pragmatics, 11(6):689–719. find
Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In Proceedings of the International Conference of Machine Learning. find
Mohit Iyyer, John Wieting, Kevin Gimpel, and Luke Zettlemoyer. 2018. Adversarial example generation with syntactically controlled paraphrase networks. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1875–1885, New Orleans, Louisiana. Association for Computational Linguistics. find
Unnat Jain, Ziyu Zhang, and Alexander G Schwing. 2017. Creativity: Generating diverse questions using variational autoencoders. In Computer Vision and Pattern Recognition. find
Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations. find
Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander Rush. 2017. OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations. find
Stanley Kok and Chris Brockett. 2010. Hitting the right paraphrases in good time. In Conference of the North American Chapter of the Association for Computational Linguistics. Association for Computational Linguistics. find
Ashutosh Kumar, Satwik Bhattamishra, Manik Bhandari, and Partha Talukdar. 2019. Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation. In Conference of the North American Chapter of the Association for Computational Linguistics. find
Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018. Unsupervised machine translation using monolingual corpora only. In Proceedings of the International Conference on Learning Representations. find
J Richard Landis and Gary G Koch. 1977. The measurement of observer agreement for categorical data. biometrics, pages 159–174. find
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461. ↗
Jiwei Li, Will Monroe, and Dan Jurafsky. 2016. A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:1611.08562. ↗
Juncen Li, Robin Jia, He He, and Percy Liang. 2018. 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), pages 1865–1874, New Orleans, Louisiana. Association for Computational Linguistics. find our card
Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, and Joseph E Gonzalez. 2020. Train large, then compress: Rethinking model size for efficient training and inference of transformers. arXiv preprint arXiv:2002.11794. ↗
Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of Empirical Methods in Natural Language Processing. find
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. ↗
Lajanugen Logeswaran, Honglak Lee, and Samy Bengio. 2018. Content preserving text generation with attribute controls. In Proceedings of Advances in Neural Information Processing Systems. find
Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Xu Sun, and Zhifang Sui. 2019. A dual reinforcement learning framework for unsupervised text style transfer. In International Joint Conference on Artificial Intelligence. find
Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Effective approaches to attention-based neural machine translation. In Proceedings of Empirical Methods in Natural Language Processing. find
Yun Ma, Yangbin Chen, Xudong Mao, and Qing Li. 2019. A syntax-aware approach for unsupervised text style transfer. OpenReview. find
Aman Madaan, Amrith Setlur, Tanmay Parekh, Barnabas Poczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W Black, and Shrimai Prabhumoye. 2020. Politeness transfer: A tag and generate approach. In Proceedings of the Association for Computational Linguistics. find
M. Meyerhoff. 2015. Taylor & Francis. Introducing Sociolinguistics. find
Remi Mir, Bjarke Felbo, Nick Obradovich, and Iyad Rahwan. 2019. Evaluating style transfer for text. In Conference of the North American Chapter of the Association for Computational Linguistics. find
Shuyo Nakatani. 2010. Language detection library for java. find
Jekaterina Novikova, Ondřej Dušek, Amanda Cercas Curry, and Verena Rieser. 2017. Why we need new evaluation metrics for NLG. In Proceedings of Empirical Methods in Natural Language Processing. find
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019. fairseq: A fast, extensible toolkit for sequence modeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). find
Richard Yuanzhe Pang. 2019. Towards actual (not operational) textual style transfer auto-evaluation. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). find
Richard Yuanzhe Pang and Kevin Gimpel. 2019. Unsupervised evaluation metrics and learning criteria for non-parallel textual transfer. In Proceedings of the 3rd Workshop on Neural Generation and Translation. find
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the Association for Computational Linguistics. Association for Computational Linguistics. find our card
Sunghyun Park, Seung-won Hwang, Fuxiang Chen, Jaegul Choo, Jung-Woo Ha, Sunghun Kim, and Jinyeong Yim. 2019. Paraphrase diversification using counterfactual debiasing. In Association for the Advancement of Artificial Intelligence. find
Hao Peng, Ankur Parikh, Manaal Faruqui, Bhuwan Dhingra, and Dipanjan Das. 2019. Text generation with exemplar-based adaptive decoding. In Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota. Association for Computational Linguistics. find
Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. 2018. Style transfer through back-translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 866–876, Melbourne, Australia. Association for Computational Linguistics. find
Sandeep Subramanian, Guillaume Lample, Eric Michael Smith, Ludovic Denoyer, Marc’Aurelio Ranzato, and Y-Lan Boureau. 2019. Multiple-attribute text style transfer. In Proceedings of the International Conference on Learning Representations. find
Daniel Preotiuc-Pietro, Wei Xu, and Lyle Ungar. 2016. Discovering user attribute stylistic differences via paraphrasing. In Association for the Advancement of Artificial Intelligence. find
Akhilesh Sudhakar, Bhargav Upadhyay, and Arjun Maheswaran. 2019. “transforming” delete, retrieve, generate approach for controlled text style transfer. In Proceedings of Empirical Methods in Natural Language Processing. find
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog, 1(8). find
Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of Advances in Neural Information Processing Systems, pages 3104–3112. find
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683. ↗
Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan, Vasudeva Varma, et al. 2020. Adapting language models for non-parallel author-stylized rewriting. In Association for the Advancement of Artificial Intelligence. find
Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of Empirical Methods in Natural Language Processing. find
Alexey Tikhonov, Viacheslav Shibaev, Aleksander Nagaev, Aigul Nugmanova, and Ivan P Yamshchikov. 2019. Style transfer for texts: Retrain, report errors, compare with rewrites. In Proceedings of Empirical Methods in Natural Language Processing. find
Sudha Rao and Joel Tetreault. 2018. Dear sir or madam, may I introduce the GYAFC dataset: Corpus, benchmarks and metrics for formality style transfer. In Conference of the North American Chapter of the Association for Computational Linguistics. find our card
Cicero Nogueira dos Santos, Igor Melnyk, and Inkit Padhi. 2018. Fighting offensive language on social media with unsupervised text style transfer. In Proceedings of the Association for Computational Linguistics. find
Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020. BLEURT: Learning robust metrics for text generation. In Proceedings of the Association for Computational Linguistics. find
Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine translation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 86–96, Berlin, Germany. Association for Computational Linguistics. find
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of Advances in Neural Information Processing Systems, pages 5998–6008. find
Ashwin K Vijayakumar, Michael Cogswell, Ramprasaath R Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra. 2018. Diverse beam search for improved description of complex scenes. In Association for the Advancement of Artificial Intelligence. find
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the International Conference of Machine Learning, pages 1096–1103. find
Alex Wang, Kyunghyun Cho, and Mike Lewis. 2020. Asking and answering questions to evaluate the factual consistency of summaries. In Proceedings of the Association for Computational Linguistics. find
Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in neural information processing systems, pages 6830–6841. find our card
Alex Warstadt, Amanpreet Singh, and Samuel R Bowman. 2019. Neural network acceptability judgments. Transactions of the Association for Computational Linguistics. find
Rakshith Shetty, Bernt Schiele, and Mario Fritz. 2018. A4nt: author attribute anonymity by adversarial training of neural machine translation. In 27th {USENIX} Security Symposium ({USENIX} Security 18), pages 1633–1650. find
John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel, and Graham Neubig. 2019. Beyond BLEU:training neural machine translation with semantic similarity. In Proceedings of the Association for Computational Linguistics. find
John Wieting and Kevin Gimpel. 2018. ParaNMT-50M: Pushing the limits of paraphrastic sentence embeddings with millions of machine translations. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 451–462, Melbourne, Australia. Association for Computational Linguistics. find
Sam Wiseman, Stuart Shieber, and Alexander Rush. 2018. Learning neural templates for text generation. In Proceedings of Empirical Methods in Natural Language Processing. find
Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, R’emi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace’s Transformers: State-of-the-art natural language processing. ArXiv, abs/1910.03771. ↗
Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. 2018. Transfertransfo: A transfer learning approach for neural network based conversational agents. In NeurIPS CAI Workshop. find
Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong, and Quoc V Le. 2019. Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848. ↗
Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, and Wenjie Li. 2018. Unpaired sentiment-to-sentiment translation: A cycled reinforcement learning approach. In Proceedings of the Association for Computational Linguistics. find
Wei Xu, Chris Callison-Burch, and Courtney Napoles. 2015. Problems in current text simplification research: New data can help. Transactions of the Association for Computational Linguistics, 3:283–297. find
Wei Xu, Alan Ritter, Bill Dolan, Ralph Grishman, and Colin Cherry. 2012. Paraphrasing for style. In Proceedings of International Conference on Computational Linguistics. find our card
Zichao Yang, Zhiting Hu, Chris Dyer, Eric P Xing, and Taylor Berg-Kirkpatrick. 2018. Unsupervised text style transfer using language models as discriminators. In Proceedings of Advances in Neural Information Processing Systems. find
Kuo-Hao Zeng, Mohammad Shoeybi, and Ming-Yu Liu. 2020. Style example-guided text generation using generative adversarial transformers. arXiv preprint arXiv:2003.00674. ↗
Zhirui Zhang, Shuo Ren, Shujie Liu, Jianyong Wang, Peng Chen, Mu Li, Ming Zhou, and Enhong Chen. 2018. Style transfer as unsupervised machine translation. arXiv preprint arXiv:1808.07894. ↗
Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/krishna-2020-reformulating-unsupervised-style-transfer-as/