{"type":"ScholarlyArticle","title":"Text Style Transfer via Learning Style Instance Supported Latent Space","authors":[{"name":"Xiaoyuan Yi","slug":"xiaoyuan-yi","given":"Xiaoyuan","family":"Yi","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University"},{"name":"Zhenghao Liu","slug":"zhenghao-liu","given":"Zhenghao","family":"Liu","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University"},{"name":"Wenhao Li","slug":"wenhao-li","given":"Wenhao","family":"Li","affiliation":"Department of Computer Science and Technology , Tsinghua University"},{"name":"Maosong Sun","slug":"maosong-sun","given":"Maosong","family":"Sun","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Jiangsu Collaborative Innovation Center for Language Ability , Jiangsu Normal University"}],"abstract":"Text style transfer pursues altering the style of a sentence while remaining its main content unchanged. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and has achieved noticeable progress. Nonetheless, the intractability of completely disentangling content from style for text leads to a contradiction of content preservation and style transfer accuracy. To address this problem, we propose a style instance supported method, StyIns. Instead of representing styles with embeddings or latent variables learned from single sentences, our model leverages the generative flow technique to extract underlying stylistic properties from multiple instances of each style, which form a more discriminative and expressive latent style space. By combining such a space with the attention-based structure, our model can better maintain the content and simultaneously achieve high transfer accuracy. Furthermore, the proposed method can be flexibly extended to semi-supervised learning so as to utilize available limited paired data. Experiments on three transfer tasks, sentiment modification, formality rephrasing, and poeticness generation, show that StyIns obtains a better balance between content and style, outperforming several recent baselines.","doi":"10.24963/ijcai.2020/526","url":"https://ijcai.org/proceedings/2020/526","pdf":"https://ijcai.org/proceedings/2020/0526.pdf","markdown":"https://ijcai.org/proceedings/2020/526.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/526","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":526,"pages":{"first":3801,"last":3807},"keywords":["Natural Language Processing: Natural Language Generation","Natural Language Processing: Natural Language Processing"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24313/file_24313.m3u8","length_sec":287,"provider":"hls"}],"references":[{"position":1,"raw":"[Atanov et al., 2019] Andrei Atanov, Arsenii Ashukha, Kir- ill Struminsky, Dmitry Vetrov, and Max Welling. The deep weight prior. In ICLR, 2019.","title":"The deep weight prior","authors":"Atanov","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bahdanau et al., 2015] Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In ICLR, 2015.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Crystal, 1970] David Crystal. New perspectives for lan- guage study. 1:stylistics. English Language Teaching, 24(2):99-106, 1970.","title":"David Crystal. New perspectives for language study. 1:stylistics","authors":"Crystal","year":"1970","venue":"English Language Teaching","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dai et al., 2019] Ning Dai, Jianze Liang, Xipeng Qiu, and Xuanjing Huang. Style transformer: Unpaired text style transfer without disentangled latent representation. In ACL, pages 5997-6007, 2019.","title":"Style transformer: Unpaired text style transfer without disentangled latent representation","authors":"Ning Dai, Jianze Liang, Xipeng Qiu, Xuanjing Huang","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understand- ing. In NAACL-HLT, pages 4171-4186, 2019.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Embler, 1967] Weller Embler. Style is as style does. ETC: A Review of General Semantics, 24(4):447-454, 1967.","title":"Style is as style does","authors":"Weller Embler","year":"1967","venue":"ETC: A Review of General Semantics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fu et al., 2018] Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. Style transfer in text: Ex- ploration and evaluation. In AAAI, pages 663-670, 2018.","title":"Style transfer in text: Exploration and evaluation","authors":"Fu","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Germain et al., 2015] Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle. Made: Masked autoen- coder for distribution estimation. In ICML, 2015.","title":"Made: Masked autoencoder for distribution estimation","authors":"Karol Mathieu Germain, Iain Gregor, Hugo Murray, Larochelle","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gong et al., 2019] Hongyu Gong, Suma Bhat, Lingfei Wu, JinJun Xiong, and Wen-mei Hwu. Reinforcement learning based text style transfer without parallel training corpus. In NAACL-HLT, pages 3168-3180, 2019.","title":"Reinforcement learning based text style transfer without parallel training corpus","authors":"Hongyu Gong, Suma Bhat, Lingfei Wu, Jinjun Xiong, Wen-Mei Hwu","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In NeurIPS, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Heafield, 2011] Kenneth Heafield. KenLM: Faster and smaller language model queries. In Proceedings of the Sixth Workshop on Statistical Machine Translation, 2011.","title":"KenLM: Faster and smaller language model queries","authors":"Kenneth Heafield","year":"2011","venue":"Proceedings of the Sixth Workshop on Statistical Machine Translation","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ide, 2004] Nancy Ide. Preparation and analysis of linguistic corpora. A Companion to digital Humanities, 27:278-305, 2004.","title":"Preparation and analysis of linguistic corpora","authors":"Nancy Ide","year":"2004","venue":"A Companion to digital Humanities","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[John et al., 2019] Vineet John, Lili Mou, Hareesh Bahu- leyan, and Olga Vechtomova. Disentangled representation learning for non-parallel text style transfer. In ACL, pages 424-434, 2019.","title":"Disentangled representation learning for non-parallel text style transfer","authors":"Vineet John, Lili Mou, Hareesh Bahuleyan, Olga Vechtomova","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Welling, 2014] Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. In ICLR, 2014.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kingma et al., 2016] Durk P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, and Max Welling. Improved variational inference with inverse autoregressive flow. In NeurIPS, 2016.","title":"Improved variational inference with inverse autoregressive flow","authors":"P Durk, Tim Kingma, Rafal Salimans, Xi Jozefowicz, Ilya Chen, Max Sutskever, Welling","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lample et al., 2019] Guillaume Lample, Sandeep Subrama- nian, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, and Y-Lan Boureau. Multiple-attribute text rewriting. In ICLR, 2019.","title":"Multiple-attribute text rewriting","authors":"Guillaume Lample, Sandeep Subramanian, Eric Michael Smith, Ludovic Denoyer, Marc'aurelio Ranzato, Y-Lan Boureau","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2018] Juncen Li, Robin Jia, He He, and Percy Liang. Delete, retrieve, generate: a simple approach to sentiment and style transfer. In NAACL-HLT, pages 1865- 1874, 2018.","title":"Delete, retrieve, generate: a simple approach to sentiment and style transfer","authors":"Li","year":"2018","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Luo et al., 2019] Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Xu Sun, and Zhifang Sui. A dual reinforcement learning framework for unsupervised text style transfer. In IJCAI, pages 5116-5122, 2019.","title":"A dual reinforcement learning framework for unsupervised text style transfer","authors":"Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Xu Sun, Zhifang Sui","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/711"},{"position":19,"raw":"[Miyato et al., 2018] T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshid. Spectral normalization for generative ad- versarial networks. In ICLR, 2018.","title":"Spectral normalization for generative adversarial networks","authors":"T Miyato, T Kataoka, M Koyama, Y Yoshid","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Prabhumoye et al., 2018] Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. Style transfer through back-translation. In ACL, 2018.","title":"Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. Style transfer through back-translation","authors":"Prabhumoye","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rao and Tetreault, 2018] Sudha Rao and Joel Tetreault. Dear sir or madam, may i introduce the gyafc dataset: Cor- pus, benchmarks and metrics for formality style transfer. In NAACL-HLT, pages 129-140, 2018.","title":"Dear sir or madam, may i introduce the gyafc dataset: Corpus, benchmarks and metrics for formality style transfer","authors":"Sudha Rao, Joel Tetreault","year":"2018","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rezende and Mohamed, 2015] Danilo Jimenez Rezende and Shakir Mohamed. Variational inference with normalizing flows. In ICML, pages 1530-1538, 2015.","title":"Variational inference with normalizing flows","authors":"Mohamed ; Rezende, Danilo Jimenez, Rezende, Shakir Mohamed","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shang et al., 2019] Mingyue Shang, Piji Li, Zhenxin Fu, Li- dong Bing, Dongyan Zhao, Shuming Shi, and Rui Yan. Semi-supervised text style transfer: Cross projection in la- tent space. In EMNLP-IJCNLP, pages 4936-4945, 2019.","title":"Semi-supervised text style transfer: Cross projection in latent space","authors":"Mingyue Shang, Piji Li, Zhenxin Fu, Lidong Bing, Dongyan Zhao, Shuming Shi, Rui Yan","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shen et al., 2017] Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. Style transfer from non-parallel text by cross-alignment. In NeurIPS, 2017.","title":"Style transfer from non-parallel text by cross-alignment","authors":"Shen","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 6000-6010, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wu et al., 2019a] Chen Wu, Xuancheng Ren, Fuli Luo, and Xu Sun. A hierarchical reinforced sequence operation method for unsupervised text style transfer. In ACL, pages 4873-4883, 2019.","title":"A hierarchical reinforced sequence operation method for unsupervised text style transfer","authors":"Wu","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wu et al., 2019b] Xing Wu, Tao Zhang, Liangjun Zang, Jizhong Han, and Songlin Hu. Mask and infill: Applying masked language model to sentiment transfer. In IJCAI, pages 5271-5277, 2019.","title":"Mask and infill: Applying masked language model to sentiment transfer","authors":"Wu","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yang et al., 2018] Zichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, and Taylor Berg-Kirkpatrick. Unsupervised text style transfer using language models as discrimina- tors. In NeurIPS, 2018.","title":"Unsupervised text style transfer using language models as discriminators","authors":"Yang","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yi et al., 2018] Xiaoyuan Yi, Maosong Sun, Ruoyu Li, and Wenhao Li. Automatic poetry generation with mutual re- inforcement learning. In EMNLP, pages 3143-3153, 2018.","title":"Automatic poetry generation with mutual reinforcement learning","authors":"Xiaoyuan Yi, Maosong Sun, Ruoyu Li, Wenhao Li","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2018] Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. Emotional chatting machine: Emotional conversation generation with interna- land external memory. In AAAI, pages 730-738, 2018.","title":"Emotional chatting machine: Emotional conversation generation with internaland external memory","authors":"Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, Bing Liu","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2017] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image transla- tionusing cycle-consistent adversarial networks. In ICCV, pages 2223-2232, 2017.","title":"Unpaired image-to-image translationusing cycle-consistent adversarial networks","authors":"Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A Efros","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}